diff --git a/dot_claude/commands/bd-drain.md b/dot_claude/commands/bd-drain.md
deleted file mode 100644
index 0ce7fb0..0000000
--- a/dot_claude/commands/bd-drain.md
+++ /dev/null
@@ -1,118 +0,0 @@
----
-description: Recursively implement all pending beads issues until every one is closed with tests passing, builds succeeding, requirements met, and blockers cleared
-argument-hint: [optional: priority filter e.g. "p0-p2" | epic id | "dry-run"]
-allowed-tools: Bash(bd:*), Bash(git:*), Bash(go:*), Bash(pnpm:*), Bash(cargo:*), Bash(make:*), Read, Write, Edit, Glob, Grep, Task
----
-
-# /bd-drain — Recursive Beads Completion Workflow
-
-Drain the beads backlog to zero. Work every ready issue to full completion, unblock dependent issues as they clear, and repeat until no open, actionable work remains. Arguments: `$ARGUMENTS` (optional priority filter like `p0-p2`, an epic ID to scope to, or `dry-run` to plan without executing).
-
-## Phase 0 — Session Bootstrap
-
-1. Run `bd dolt pull` to sync beads state from remote.
-2. Run `bd prime` if context was compacted or this is a fresh session.
-3. Run `bd doctor` — if sync problems or missing hooks are reported, fix them before proceeding.
-4. Run `bd stats` and record the baseline: open / in_progress / blocked counts. This is the burn-down target.
-5. Run `bd memories drain` and `bd memories <project keyword>` to load any prior insights about this workflow or codebase gotchas.
-6. Detect the project's verification commands by inspecting the repo (Makefile, Taskfile, turbo.json, package.json scripts, go.mod, Cargo.toml). Record:
-   - **TEST_CMD** (e.g. `go test ./...`, `pnpm turbo test`, `cargo test`)
-   - **BUILD_CMD** (e.g. `go build ./...`, `pnpm turbo build`)
-   - **LINT_CMD** if present (e.g. `golangci-lint run`, `pnpm lint`)
-7. Run TEST_CMD and BUILD_CMD once **before touching anything** to establish a green baseline. If the baseline is already red, create a P0 bug with `bd create` describing the pre-existing failure and fix it first — never build on a broken base.
-
-If `$ARGUMENTS` contains `dry-run`: execute Phase 1's triage, print the planned execution order as a dependency-sorted list, and STOP.
-
-## Phase 1 — Triage & Ordering
-
-1. Run `bd ready` for actionable issues (respect `$ARGUMENTS` priority/epic filter if given).
-2. Run `bd blocked` and `bd show <id>` on each blocked issue to map the dependency graph.
-3. Run `bd orphans` — repair or flag any broken dependencies (`bd dep add` / `bd human <id>`).
-4. Build a topologically-sorted work queue: priority order (P0 → P4) within dependency order. Issues whose completion unblocks the most downstream work get tie-breaker preference.
-5. Run `bd lint` on the queue. For issues with missing/vague requirements, attempt to infer acceptance criteria from the description and codebase, update via `bd update <id> --acceptance="..."`. If requirements are genuinely undecidable, run `bd human <id>` with a specific question and skip it (do not guess on ambiguous product decisions).
-
-## Phase 2 — The Drain Loop
-
-Repeat until the exit condition in Phase 3 is met. For **each** issue in the queue:
-
-### 2a. Claim
-```bash
-bd show <id>            # re-read full details, dependencies, acceptance criteria
-bd update <id> --claim  # mark in_progress
-```
-
-### 2b. Implement
-- Read the acceptance criteria, design notes, and any linked issues before writing code.
-- Locate the relevant code with Glob/Grep; understand existing patterns before adding new ones.
-- Implement the minimal complete change that satisfies the requirements. Follow existing repo conventions.
-- If the issue is a `feature` without tests specified, write tests anyway — untested features do not count as done.
-- If during implementation you discover necessary sub-work, create it immediately: `bd create --title="..." --description="..." --type=task --priority=<match parent>` then `bd dep add <new-id> <current-id>` as appropriate. Never leave discovered work untracked.
-
-### 2c. Verify (hard gates — ALL must pass)
-```bash
-<TEST_CMD>    # full test suite, not just new tests
-<BUILD_CMD>   # full build
-<LINT_CMD>    # if present
-```
-- ✅ All tests pass (including pre-existing ones — no regressions)
-- ✅ Build succeeds cleanly
-- ✅ Every acceptance criterion on the issue is demonstrably met
-- ✅ No new warnings/lint errors introduced
-
-On failure: fix and re-verify. After **3 failed fix attempts** on the same root cause, stop thrashing — record findings with `bd update <id> --notes="<what was tried, error output, hypothesis>"`, run `bd human <id>` if it needs a decision, revert the working tree to the last green state, and move to the next issue.
-
-### 2d. Close & Checkpoint
-```bash
-bd close <id> --reason="<one-line summary of what was done>" --suggest-next
-bd remember "<any non-obvious insight learned: gotcha, pattern, decision>"
-git add <changed files>
-git commit -m "<type>(<scope>): <summary> (closes <id>)"
-```
-- Commit per issue, not in batches — each commit should be independently green.
-- `--suggest-next` output feeds Phase 2e.
-
-### 2e. Re-plan
-- Newly unblocked issues from `--suggest-next` are inserted into the queue in priority order.
-- Every **5 closed issues**, re-run `bd ready` and `bd blocked` to catch drift (issues added by hooks, remote changes), and re-run the full test suite even if the last issue didn't touch shared code.
-
-### Parallelism
-When the queue contains **independent** issues (no shared files, no dependency relation), dispatch up to 3 in parallel via the Task tool (subagents), each following 2a–2d in isolation. Serialize anything touching shared modules, migrations, or config. Merge subagent commits sequentially and re-run TEST_CMD after each merge.
-
-## Phase 3 — Exit Conditions & Escalation
-
-The loop terminates when **one** of these holds:
-
-1. **Success**: `bd ready` is empty AND `bd blocked` is empty (within the `$ARGUMENTS` scope) AND the final full TEST_CMD + BUILD_CMD run is green.
-2. **Human-gated**: remaining issues are all flagged via `bd human` — report them with the specific decision needed for each.
-3. **Externally blocked**: remaining blockers depend on things outside this repo (third-party, credentials, other teams) — document each with `bd update <id> --notes` and report.
-
-Never terminate by silently skipping issues. Every open issue at exit must be either human-flagged or externally blocked with notes explaining why.
-
-## Phase 4 — Session Close Protocol (MANDATORY)
-
-```bash
-[ ] git status              # confirm nothing unstaged/untracked left behind
-[ ] git add <files>         # stage any stragglers
-[ ] bd dolt pull            # pull beads updates from main
-[ ] git commit -m "..."     # final commit if anything staged
-[ ] bd stats                # final counts
-```
-
-Then produce the **Drain Report**:
-
-- **Burn-down**: baseline vs final counts (open / in_progress / blocked / closed this session)
-- **Closed**: each issue ID + one-line summary + commit SHA
-- **Escalated**: each `bd human` flag with the exact decision needed
-- **Externally blocked**: each with the external dependency named
-- **Discovered work**: new issues created during the drain
-- **Insights recorded**: `bd remember` entries added
-- **Final verification**: test suite result, build result, lint result
-
-## Hard Rules
-
-- Use beads for ALL tracking. Never TodoWrite, TaskCreate, or markdown task files.
-- Never `bd edit` (blocks on $EDITOR).
-- Never close an issue whose acceptance criteria aren't verifiably met — a passing build is necessary, not sufficient.
-- Never commit with a red test suite.
-- Priority values are numeric (0–4 / P0–P4), never "high"/"medium"/"low".
-- Persistence you don't need beats lost context: over-record notes, insights, and reasons.
diff --git a/dot_claude/commands/cmem-to-beads.md b/dot_claude/commands/cmem-to-beads.md
deleted file mode 100644
index 03e8696..0000000
--- a/dot_claude/commands/cmem-to-beads.md
+++ /dev/null
@@ -1,140 +0,0 @@
----
-description: Extract insight-type learnings from claude-mem and record them into beads memories
----
-
-# Sync claude-mem insights → beads memories
-
-<!--toc:start-->
-- [Sync claude-mem insights → beads memories](#sync-claude-mem-insights-beads-memories)
-  - [Scope (read carefully)](#scope-read-carefully)
-  - [Phase 0 — Preflight](#phase-0-preflight)
-  - [Phase 1 — Enumerate ALL learnings (the loop)](#phase-1-enumerate-all-learnings-the-loop)
-  - [Phase 2 — Triage & record (per-item loop)](#phase-2-triage-record-per-item-loop)
-  - [Phase 3 — Finalize](#phase-3-finalize)
-  - [Guardrails](#guardrails)
-<!--toc:end-->
-
-You are migrating **durable insights** from **claude-mem** (the session memory store)
-into **beads** (`bd remember`) for this repository. Work autonomously through a loop
-until every relevant observation has been triaged. Do not invent learnings — only
-persist what claude-mem actually returns.
-
-## Scope (read carefully)
-
-- **Record ONLY insights / decisions / gotchas** → `bd remember`.
-- **Ignore actionable learnings** (bugs to fix, tech debt, follow-ups, TODOs).
-  Do **not** create them as beads issues. A separate command will later pull those
-  from claude-mem and feed them into **Linear** for PM; beads then syncs from Linear.
-- This command therefore **never calls `bd create`** and never writes beads issues.
-  The only write to beads is `bd remember`. Leave actionable items untouched in
-  claude-mem so the future Linear command can pick them up.
-
----
-
-## Phase 0 — Preflight
-
-1. Confirm beads is live in this repo: `bd ready` (and `bd doctor` if it errors).
-2. Snapshot existing memories for dedup: `bd memories ""` (plus a few broad keyword
-   `bd memories <term>` lookups) and keep the gist in mind.
-3. Set up a **local progress file** for resumability (so compaction/re-runs skip done
-   work) — NOT a beads issue:
-   ```
-   ./.claude-mem-sync/processed.json    # { "processed": [<cmem ids>], "skipped_actionable": <count> }
-   ```
-   Create it if missing; load it if present. Add `.claude-mem-sync/` to `.gitignore`
-   if it isn't already.
-
----
-
-## Phase 1 — Enumerate ALL learnings (the loop)
-
-claude-mem search is query-based, so a single call won't surface everything. Build a
-**complete, de-duplicated set of observation IDs** by sweeping across angles, then
-walking chronologically. Track seen IDs in a set; never process the same ID twice.
-
-Use `/claude-mem:mem-search` for every query below, following claude-mem's 3-layer
-pattern — pull the compact **index** first, only fetch full details for IDs you keep.
-
-**1a. Type sweep** — one broad query per observation type, high limit:
-```
-/claude-mem:mem-search  (type=insight)
-/claude-mem:mem-search  (type=decision)
-/claude-mem:mem-search  (type=bugfix)        # scan for the *lesson learned*, not the fix-task
-/claude-mem:mem-search  (type=architecture)
-/claude-mem:mem-search  (type=feature)       # plus any other types this project uses
-```
-> You still scan every type — a bugfix or feature observation often contains a durable
-> *insight* ("X breaks when Y") even though its actionable part is ignored here.
-
-**1b. Topic sweep** — queries for the repo's recurring themes (infer from the codebase:
-auth, deploy, config, performance, gotchas, "why we", "decided", "learned", "don't").
-Each adds new IDs to the set.
-
-**1c. Chronological walk** — to catch what the sweeps missed, seed `timeline` from your
-earliest and latest known observations and step through history, collecting any IDs not
-already in the set. Stop when the timeline yields no new IDs in either direction.
-
-Result: a deduplicated list of candidate observation IDs. Print the count.
-
----
-
-## Phase 2 — Triage & record (per-item loop)
-
-Process candidate IDs in batches. For each batch:
-
-1. **Fetch details** once: `get_observations(ids=[...])` (batch IDs — never one-at-a-time).
-2. For **each** observation, classify:
-
-   - **Actionable** (a thing to *do*: unfixed bug, tech debt, follow-up, TODO) →
-     **IGNORE**. Increment `skipped_actionable` in the progress file and move on.
-     It stays in claude-mem for the Linear command.
-
-   - **Insight / decision / gotcha** (durable knowledge about *how things are*) →
-     record it:
-     - **Dedup check** first: `bd memories <key terms>`. If beads already captures it, skip.
-     - Then:
-       ```
-       bd remember "<one-line durable insight, self-contained, no session context> [cmem #<id>]"
-       ```
-       Keep it atomic and reusable. Include the source `cmem #<id>` so it traces back
-       to http://localhost:37777/api/observation/<id>.
-
-   - **Noise** (one-off output, ephemeral state, trivially obvious, duplicate) → skip silently.
-
-3. Append processed IDs to `./.claude-mem-sync/processed.json`.
-
-Repeat until the candidate set is exhausted.
-
----
-
-## Phase 3 — Finalize
-
-1. Sanity pass: `bd memories ""` — confirm new insights landed and read cleanly.
-2. Sync beads memories to remote: `bd dolt push`.
-3. **Session close protocol** — if any code/files changed (e.g. `.gitignore`):
-   ```
-   git status
-   git add <files>
-   git commit -m "chore: record claude-mem insights into beads"
-   git push
-   ```
-
----
-
-## Guardrails
-
-- **Insights only.** Never `bd create`, never write a beads issue. Actionable items are
-  ignored and left in claude-mem for the Linear sync command.
-- **Idempotent.** Re-running must not duplicate — always dedup against `bd memories` and
-  the local progress file before writing.
-- **Atomic memories.** One insight per `bd remember`, self-contained, no "in this session"
-  phrasing.
-- **Cite the source.** Every entry carries its `cmem #<id>` for traceability.
-- **No `bd edit`** — it opens an editor and blocks.
-- **Don't fabricate** — if a sweep returns nothing, say so and move on.
-- For large sets, run the type/topic sweeps and `bd memories` dedup lookups with
-  **parallel subagents** for speed.
-
-When done, report: total observations scanned, how many insights were recorded, how many
-were skipped as **actionable** (this is the backlog the Linear command will handle), and
-how many were skipped as noise/duplicates.
diff --git a/dot_claude/commands/cmem-to-linear.md b/dot_claude/commands/cmem-to-linear.md
deleted file mode 100644
index 84d96c9..0000000
--- a/dot_claude/commands/cmem-to-linear.md
+++ /dev/null
@@ -1,179 +0,0 @@
----
-description: Extract actionable learnings from claude-mem into beads tasks and push them up to Linear for PM
----
-
-# Sync claude-mem actionable learnings → beads → Linear
-
-<!--toc:start-->
-- [Sync claude-mem actionable learnings → beads → Linear](#sync-claude-mem-actionable-learnings-beads-linear)
-  - [Scope (read carefully)](#scope-read-carefully)
-  - [Sync model (no linear-cli needed)](#sync-model-no-linear-cli-needed)
-  - [Phase 0 — Preflight](#phase-0-preflight)
-  - [Phase 1 — Enumerate ALL learnings (the loop)](#phase-1-enumerate-all-learnings-the-loop)
-  - [Phase 2 — Triage & create (per-item loop)](#phase-2-triage-create-per-item-loop)
-  - [Phase 3 — Push to Linear](#phase-3-push-to-linear)
-  - [Phase 4 — Finalize](#phase-4-finalize)
-  - [Guardrails](#guardrails)
-<!--toc:end-->
-
-You are turning **actionable learnings** from **claude-mem** (the session memory store)
-into **beads** (`bd`) tasks, then pushing the new ones up to **Linear** for PM. Work
-autonomously through a loop until every relevant observation has been triaged. Do not
-invent learnings — only persist what claude-mem actually returns.
-
-## Scope (read carefully)
-
-- **Record ONLY actionable learnings** — things to *do*: unfixed bugs, tech debt,
-  follow-ups, TODOs, missing tests, planned refactors. Each becomes a `bd create` task.
-- **Ignore insights / decisions / gotchas** (durable knowledge about *how things are*).
-  A separate command records those as `bd remember` memories — do **not** touch them here.
-  Leave them in claude-mem untouched.
-- A single observation may legitimately contain both an insight *and* an action item; the
-  two commands are independent, so it's fine if this one creates a task while the other
-  records a memory from the same `cmem #<id>`.
-
-## Sync model (no linear-cli needed)
-
-Beads-first, push up, bidirectional thereafter:
-1. Create tasks in beads (`bd create`).
-2. Push the new ones to Linear with `bd linear push <ids>` — this creates the Linear
-   issues and writes `external_ref` back onto each bead (`--update-refs` is default true).
-3. From then on, `bd linear sync` is bidirectional: PM edits in Linear pull back into beads.
-
-`linear-cli` is **not** used. All Linear interaction goes through native `bd linear`.
-
----
-
-## Phase 0 — Preflight
-
-1. Confirm beads is live: `bd ready` (and `bd doctor` if it errors).
-2. Confirm Linear is wired up: `bd linear status`. If it errors / unconfigured, stop and
-   tell the user to set `linear.api_key` + team (`bd linear teams` to find the team UUID).
-   Note whether **multiple teams** are configured (`linear.team_ids`) — if so, push needs
-   an explicit `--team <ID>`; ask the user which team these tasks belong to.
-3. Dedup snapshot: `bd list --status=open` and a few `bd search <term>` lookups so you can
-   recognize existing tasks (including ones already pulled from Linear).
-4. Local progress file for resumability — NOT a beads issue:
-   ```
-   ./.claude-mem-sync/processed-actions.json   # { "processed": [<cmem ids>], "created": [<bead ids>], "skipped_insights": <n> }
-   ```
-   Create if missing, load if present. Ensure `.claude-mem-sync/` is in `.gitignore`.
-
----
-
-## Phase 1 — Enumerate ALL learnings (the loop)
-
-claude-mem search is query-based, so one call won't surface everything. Build a
-**complete, de-duplicated set of observation IDs** by sweeping across angles, then walking
-chronologically. Track seen IDs in a set; never process the same ID twice.
-
-Use `/claude-mem:mem-search` for every query below, following claude-mem's 3-layer pattern
-— pull the compact **index** first, only fetch full details for IDs you keep.
-
-**1a. Type sweep** — one broad query per observation type, high limit:
-```
-/claude-mem:mem-search  (type=bugfix)
-/claude-mem:mem-search  (type=feature)
-/claude-mem:mem-search  (type=insight)        # scan for the *action item* buried inside, not the insight
-/claude-mem:mem-search  (type=decision)
-/claude-mem:mem-search  (type=architecture)   # plus any other types this project uses
-```
-> Scan every type — even an `insight` observation often ends with "…so we should do X",
-> which is the action item you extract here while ignoring the insight itself.
-
-**1b. Topic sweep** — queries for action-shaped language the codebase tends to record:
-"TODO", "should", "need to", "fix", "broken", "flaky", "refactor", "tech debt", "later",
-"workaround", "temporary", "follow up". Each adds new IDs to the set.
-
-**1c. Chronological walk** — seed `timeline` from your earliest and latest known
-observations and step through history, collecting any IDs not already in the set. Stop when
-the timeline yields no new IDs in either direction.
-
-Result: a deduplicated list of candidate observation IDs. Print the count.
-
----
-
-## Phase 2 — Triage & create (per-item loop)
-
-Process candidate IDs in batches. For each batch:
-
-1. **Fetch details** once: `get_observations(ids=[...])` (batch IDs — never one-at-a-time).
-2. For **each** observation, classify:
-
-   - **Insight / decision / gotcha** (knowledge, nothing to *do*) → **IGNORE**. Increment
-     `skipped_insights` and move on. It's the other command's job.
-
-   - **Noise** (one-off output, ephemeral state, trivially obvious, duplicate) → skip silently.
-
-   - **Actionable** → create a task:
-     - **Dedup first:** `bd search "<key terms>"` and `bd search "cmem #<id>"`. If a matching
-       task already exists (locally or pulled from Linear), skip — this keeps re-runs idempotent.
-     - Then:
-       ```
-       bd create --title="<imperative summary>" \
-         --description="<what + why, ending with: Source: cmem #<id>>" \
-         --type=bug|task|feature \
-         --priority=<0-4>
-       ```
-       - Priority is `0-4` / `P0-P4` (0=critical … 4=backlog) — never high/medium/low.
-         bd maps this to Linear priority on push.
-       - Optionally add `--acceptance="<done criteria>"` when the observation implies one.
-       - If two items depend on each other: `bd dep add <issue> <depends-on>`.
-     - Record the new bead id and the `cmem #<id>` in the progress file.
-
-Repeat until the candidate set is exhausted.
-
----
-
-## Phase 3 — Push to Linear
-
-1. Review what's queued: `bd linear status` (shows issues pending push, i.e. no external_ref).
-2. Push **only the tasks you just created**, by id, so you don't drag along unrelated pending work:
-   ```
-   bd linear push <new-bead-id-1> <new-bead-id-2> ...
-   ```
-   - Add `--team <ID>` if multiple teams are configured (from Phase 0).
-   - Run `--dry-run` first if the user wants a preview.
-   - This creates the Linear issues and sets `external_ref` on each bead (default `--update-refs`).
-   - Alternative for bulk: `bd linear sync --push --create-only` (+ `--team`), but prefer the
-     explicit id list for precision.
-3. Confirm linkage: re-run `bd linear status` and spot-check a couple of beads now carry an
-   `external_ref` to Linear.
-
-> Steady state: after this seeding push, a scheduled or manual `bd linear sync` keeps both
-> sides aligned — PM's changes in Linear pull back down to beads. You don't push again for
-> these; you only push *newly created* tasks on future runs.
-
----
-
-## Phase 4 — Finalize
-
-1. Sync beads to its Dolt remote: `bd dolt push`.
-2. **Session close protocol** — if any code/files changed (e.g. `.gitignore`):
-   ```
-   git status
-   git add <files>
-   git commit -m "chore: extract claude-mem action items into beads + Linear"
-   git push
-   ```
-
----
-
-## Guardrails
-
-- **Actionable only.** Never `bd remember` here. Insights are ignored and left in claude-mem
-  for the insights command.
-- **No linear-cli.** All Linear interaction is native `bd linear`.
-- **Idempotent.** Re-running must not duplicate — dedup against `bd search` (including
-  `bd search "cmem #<id>"`) and the progress file before creating, and push only new ids.
-- **Cite the source.** Every task description ends with `Source: cmem #<id>`
-  (traceable at http://localhost:37777/api/observation/<id>).
-- **No `bd edit`** — it opens an editor and blocks. Use inline `--` flags on create/update.
-- **Multiple teams → explicit `--team`** on push; ask the user if ambiguous.
-- **Don't fabricate** — if a sweep returns nothing, say so and move on.
-- For large sets, run the type/topic sweeps and `bd search` dedup lookups with **parallel
-  subagents** for speed (but run `bd create` / `bd linear push` serially to keep ids ordered).
-
-When done, report: total observations scanned, how many tasks were created (with bead ids),
-how many pushed to Linear (with external_refs), how many skipped as **insights** (the other
-command's backlog), and how many skipped as noise/duplicates.
diff --git a/dot_claude/commands/create-task.md b/dot_claude/commands/create-task.md
deleted file mode 100644
index 39427b3..0000000
--- a/dot_claude/commands/create-task.md
+++ /dev/null
@@ -1,102 +0,0 @@
----
-description: Plan a task by decomposing it into beads issues with dependencies, acceptance criteria, and priorities
-argument-hint: <task description or goal>
-allowed-tools: Bash(bd:*), Bash(git log:*), Bash(git status:*), Bash(rg:*), Task
----
-
-# /create-task — Plan work into beads
-
-<!--toc:start-->
-- [/create-task — Plan work into beads](#create-task-plan-work-into-beads)
-  - [Current workspace state](#current-workspace-state)
-  - [Task to plan](#task-to-plan)
-  - [Instructions](#instructions)
-    - [1. Understand before creating](#1-understand-before-creating)
-    - [2. Decompose](#2-decompose)
-    - [3. Create issues](#3-create-issues)
-    - [4. Wire dependencies](#4-wire-dependencies)
-    - [5. Report the plan](#5-report-the-plan)
-<!--toc:end-->
-
-## Current workspace state
-
-- Ready work: !`bd ready 2>/dev/null | head -30`
-- In progress: !`bd list --status=in_progress 2>/dev/null | head -15`
-- Recently closed (dedup check): !`bd list --status=closed 2>/dev/null | head -10`
-- Stats: !`bd stats 2>/dev/null`
-- Relevant memories: !`bd memories "$ARGUMENTS" 2>/dev/null | head -40`
-
-## Task to plan
-
-$ARGUMENTS
-
-## Instructions
-
-You are planning this task using **beads as the sole tracker**. Do NOT use TodoWrite, TaskCreate, or markdown checklists. Do NOT write any code in this command — output is a set of beads issues forming an executable plan.
-
-### 1. Understand before creating
-
-- Search for prior art first: `bd search "<keywords>"` — the task (or part of it) may already exist. Per repo convention, `contracts-*`/`backend-*`/`core-*` beads mirror Linear CORE-* and share ID suffixes across sibling repos; if something looks missing, check sibling repo beads and `git log` before assuming it needs a new issue.
-- Check the injected memories above for constraints, gotchas, and prior decisions that shape the plan (e.g., root-file serialization, generated-file rules, runtime conventions).
-- If the request is ambiguous on scope, ask ONE clarifying question, then proceed.
-
-### 2. Decompose
-
-Break the task into issues sized for a single focused session (roughly ≤ half a day each). For each issue decide:
-
-- **type**: `feature` (new capability), `task` (chore/refactor/infra), `bug` (defect)
-- **priority**: numeric only — `0` critical / `1` high / `2` medium / `3` low / `4` backlog. Never "high"/"medium"/"low".
-- **description**: WHY the issue exists + WHAT done looks like. Never a bare title restatement.
-- **acceptance criteria**: concrete, verifiable (tests pass, command output, deployed address updated, etc.)
-- **design** (when a decision was made): record it so future sessions don't re-litigate.
-
-If the plan touches shared root files (`turbo.json`, `pnpm-workspace.yaml`, `pnpm-lock.yaml`, root Biome/tsconfig), note it in the issue and **serialize those issues with dependencies** — they cannot run in parallel.
-
-### 3. Create issues
-
-Use the full quality flags:
-
-```bash
-bd create \
-  --title="<imperative summary>" \
-  --description="<why + what>" \
-  --type=<task|bug|feature> \
-  --priority=<0-4> \
-  --acceptance="<verifiable criteria>" \
-  --design="<decisions, if any>" \
-  --notes="<gotchas from memories, file paths, related beads/Linear IDs>" \
-  --validate
-```
-
-- **3+ issues → spawn parallel subagents**, one `bd create` batch each, then collect the returned IDs.
-- Quote every string flag (descriptions contain `&`, `$`, backticks).
-- NEVER use `bd edit` (opens $EDITOR and blocks). Amend with `bd update <id> --description/--notes/--design`.
-
-### 4. Wire dependencies
-
-```bash
-bd dep add <dependent> <blocker>   # dependent depends on blocker
-```
-
-- Model the real execution order: tests depend on implementation, redeploys depend on ABI changes, root-file edits form a chain.
-- Verify with `bd blocked` and `bd show <id>` that the graph matches intent — no cycles, no orphans (`bd orphans`).
-
-### 5. Report the plan
-
-Output a concise summary:
-
-1. **Created issues** — table of `id | title | type | priority`
-2. **Dependency graph** — short text sketch of the ordering (e.g. `x8y → oto → 53x`)
-3. **Entry point** — which issue(s) show in `bd ready` right now, i.e., where work starts
-4. **Deferred/skipped** — anything that already existed (with the existing ID) or was intentionally left out
-
-Then persist and finish:
-
-```bash
-bd ready          # confirm entry points are unblocked
-git status        # beads auto-commits to Dolt; push if session ends here
-```
-
-If planning surfaced a durable insight (a constraint, a decision, a gotcha), store it: `bd remember "<insight>"` — never a MEMORY.md file.
-
-Do NOT start implementing any issue. Planning ends when the graph is created, validated, and reported. Implementation begins in a later session via `bd ready` → `bd update <id> --claim`.
diff --git a/dot_claude/commands/rams.md b/dot_claude/commands/rams.md
deleted file mode 100644
index 9dd06f5..0000000
--- a/dot_claude/commands/rams.md
+++ /dev/null
@@ -1,104 +0,0 @@
----
-description: Run accessibility and visual design review
----
-
-# Rams Design Review
-
-You are Rams, an expert design engineer reviewing code for accessibility and visual design issues.
-
-## Mode
-
-If `$ARGUMENTS` is provided, analyze that specific file.
-If `$ARGUMENTS` is empty, ask the user which file(s) to review, or offer to scan the project for component files.
-
----
-
-## 1. Accessibility Review (WCAG 2.1)
-
-### Critical (Must Fix)
-
-| Check | WCAG | What to look for |
-|-------|------|------------------|
-| Images without alt | 1.1.1 | `<img>` without `alt` attribute |
-| Icon-only buttons | 4.1.2 | `<button>` with only SVG/icon, no `aria-label` |
-| Form inputs without labels | 1.3.1 | `<input>`, `<select>`, `<textarea>` without associated `<label>` or `aria-label` |
-| Non-semantic click handlers | 2.1.1 | `<div onClick>` or `<span onClick>` without `role`, `tabIndex`, `onKeyDown` |
-| Missing link destination | 2.1.1 | `<a>` without `href` using only `onClick` |
-
-### Serious (Should Fix)
-
-| Check | WCAG | What to look for |
-|-------|------|------------------|
-| Focus outline removed | 2.4.7 | `outline-none` or `outline: none` without visible focus replacement |
-| Missing keyboard handlers | 2.1.1 | Interactive elements with `onClick` but no `onKeyDown`/`onKeyUp` |
-| Color-only information | 1.4.1 | Status/error indicated only by color (no icon/text) |
-| Touch target too small | 2.5.5 | Clickable elements smaller than 44x44px |
-
-### Moderate (Consider Fixing)
-
-| Check | WCAG | What to look for |
-|-------|------|------------------|
-| Heading hierarchy | 1.3.1 | Skipped heading levels (h1 → h3) |
-| Positive tabIndex | 2.4.3 | `tabIndex` > 0 (disrupts natural tab order) |
-| Role without required attributes | 4.1.2 | `role="button"` without `tabIndex="0"` |
-
----
-
-## 2. Visual Design Review
-
-### Layout & Spacing
-- Inconsistent spacing values
-- Overflow issues, alignment problems
-- Z-index conflicts
-
-### Typography
-- Mixed font families, weights, or sizes
-- Line height issues
-- Missing font fallbacks
-
-### Color & Contrast
-- Contrast ratio below 4.5:1
-- Missing hover/focus states
-- Dark mode inconsistencies
-
-### Components
-- Missing button states (disabled, loading, hover, active, focus)
-- Missing form field states (error, success, disabled)
-- Inconsistent borders, shadows, or icon sizing
-
----
-
-## Output Format
-
-```
-═══════════════════════════════════════════════════
-RAMS DESIGN REVIEW: [filename]
-═══════════════════════════════════════════════════
-
-CRITICAL (X issues)
-───────────────────
-[A11Y] Line 24: Button missing accessible name
-  <button><CloseIcon /></button>
-  Fix: Add aria-label="Close"
-  WCAG: 4.1.2
-
-SERIOUS (X issues)
-──────────────────
-...
-
-═══════════════════════════════════════════════════
-SUMMARY: X critical, X serious, X moderate
-Score: XX/100
-═══════════════════════════════════════════════════
-```
-
----
-
-## Guidelines
-
-1. Read the file(s) first before making assessments
-2. Be specific with line numbers and code snippets
-3. Provide fixes, not just problems
-4. Prioritize critical accessibility issues first
-
-If asked, offer to fix the issues directly.
diff --git a/dot_claude/commands/web-interface-guidelines.md b/dot_claude/commands/web-interface-guidelines.md
deleted file mode 100644
index c6d1a90..0000000
--- a/dot_claude/commands/web-interface-guidelines.md
+++ /dev/null
@@ -1,180 +0,0 @@
----
-description: Review UI code for Vercel Web Interface Guidelines compliance
-argument-hint: <file-or-pattern>
----
-
-# Web Interface Guidelines
-
-Review these files for compliance: $ARGUMENTS
-
-Read files, check against rules below. Output concise but comprehensive—sacrifice grammar for brevity. High signal-to-noise.
-
-## Rules
-
-### Accessibility
-
-- Icon-only buttons need `aria-label`
-- Form controls need `<label>` or `aria-label`
-- Interactive elements need keyboard handlers (`onKeyDown`/`onKeyUp`)
-- `<button>` for actions, `<a>`/`<Link>` for navigation (not `<div onClick>`)
-- Images need `alt` (or `alt=""` if decorative)
-- Decorative icons need `aria-hidden="true"`
-- Async updates (toasts, validation) need `aria-live="polite"`
-- Use semantic HTML (`<button>`, `<a>`, `<label>`, `<table>`) before ARIA
-- Headings hierarchical `<h1>`–`<h6>`; include skip link for main content
-- `scroll-margin-top` on heading anchors
-
-### Focus States
-
-- Interactive elements need visible focus: `focus-visible:ring-*` or equivalent
-- Never `outline-none` / `outline: none` without focus replacement
-- Use `:focus-visible` over `:focus` (avoid focus ring on click)
-- Group focus with `:focus-within` for compound controls
-
-### Forms
-
-- Inputs need `autocomplete` and meaningful `name`
-- Use correct `type` (`email`, `tel`, `url`, `number`) and `inputmode`
-- Never block paste (`onPaste` + `preventDefault`)
-- Labels clickable (`htmlFor` or wrapping control)
-- Disable spellcheck on emails, codes, usernames (`spellCheck={false}`)
-- Checkboxes/radios: label + control share single hit target (no dead zones)
-- Submit button stays enabled until request starts; spinner during request
-- Errors inline next to fields; focus first error on submit
-- Placeholders end with `…` and show example pattern
-- `autocomplete="off"` on non-auth fields to avoid password manager triggers
-- Warn before navigation with unsaved changes (`beforeunload` or router guard)
-
-### Animation
-
-- Honor `prefers-reduced-motion` (provide reduced variant or disable)
-- Animate `transform`/`opacity` only (compositor-friendly)
-- Never `transition: all`—list properties explicitly
-- Set correct `transform-origin`
-- SVG: transforms on `<g>` wrapper with `transform-box: fill-box; transform-origin: center`
-- Animations interruptible—respond to user input mid-animation
-
-### Typography
-
-- `…` not `...`
-- Curly quotes `"` `"` not straight `"`
-- Non-breaking spaces: `10&nbsp;MB`, `⌘&nbsp;K`, brand names
-- Loading states end with `…`: `"Loading…"`, `"Saving…"`
-- `font-variant-numeric: tabular-nums` for number columns/comparisons
-- Use `text-wrap: balance` or `text-pretty` on headings (prevents widows)
-
-### Content Handling
-
-- Text containers handle long content: `truncate`, `line-clamp-*`, or `break-words`
-- Flex children need `min-w-0` to allow text truncation
-- Handle empty states—don't render broken UI for empty strings/arrays
-- User-generated content: anticipate short, average, and very long inputs
-
-### Images
-
-- `<img>` needs explicit `width` and `height` (prevents CLS)
-- Below-fold images: `loading="lazy"`
-- Above-fold critical images: `priority` or `fetchpriority="high"`
-
-### Performance
-
-- Large lists (>50 items): virtualize (`virtua`, `content-visibility: auto`)
-- No layout reads in render (`getBoundingClientRect`, `offsetHeight`, `offsetWidth`, `scrollTop`)
-- Batch DOM reads/writes; avoid interleaving
-- Prefer uncontrolled inputs; controlled inputs must be cheap per keystroke
-- Add `<link rel="preconnect">` for CDN/asset domains
-- Critical fonts: `<link rel="preload" as="font">` with `font-display: swap`
-
-### Navigation & State
-
-- URL reflects state—filters, tabs, pagination, expanded panels in query params
-- Links use `<a>`/`<Link>` (Cmd/Ctrl+click, middle-click support)
-- Deep-link all stateful UI (if uses `useState`, consider URL sync via nuqs or similar)
-- Destructive actions need confirmation modal or undo window—never immediate
-
-### Touch & Interaction
-
-- `touch-action: manipulation` (prevents double-tap zoom delay)
-- `-webkit-tap-highlight-color` set intentionally
-- `overscroll-behavior: contain` in modals/drawers/sheets
-- During drag: disable text selection, `inert` on dragged elements
-- `autoFocus` sparingly—desktop only, single primary input; avoid on mobile
-
-### Safe Areas & Layout
-
-- Full-bleed layouts need `env(safe-area-inset-*)` for notches
-- Avoid unwanted scrollbars: `overflow-x-hidden` on containers, fix content overflow
-- Flex/grid over JS measurement for layout
-
-### Dark Mode & Theming
-
-- `color-scheme: dark` on `<html>` for dark themes (fixes scrollbar, inputs)
-- `<meta name="theme-color">` matches page background
-- Native `<select>`: explicit `background-color` and `color` (Windows dark mode)
-
-### Locale & i18n
-
-- Dates/times: use `Intl.DateTimeFormat` not hardcoded formats
-- Numbers/currency: use `Intl.NumberFormat` not hardcoded formats
-- Detect language via `Accept-Language` / `navigator.languages`, not IP
-- Brand names, code tokens, identifiers: wrap with `translate="no"` to prevent garbled auto-translation
-
-### Hydration Safety
-
-- Inputs with `value` need `onChange` (or use `defaultValue` for uncontrolled)
-- Date/time rendering: guard against hydration mismatch (server vs client)
-- `suppressHydrationWarning` only where truly needed
-
-### Hover & Interactive States
-
-- Buttons/links need `hover:` state (visual feedback)
-- Interactive states increase contrast: hover/active/focus more prominent than rest
-
-### Content & Copy
-
-- Active voice: "Install the CLI" not "The CLI will be installed"
-- Title Case for headings/buttons (Chicago style)
-- Numerals for counts: "8 deployments" not "eight"
-- Specific button labels: "Save API Key" not "Continue"
-- Error messages include fix/next step, not just problem
-- Second person; avoid first person
-- `&` over "and" where space-constrained
-
-### Anti-patterns (flag these)
-
-- `user-scalable=no` or `maximum-scale=1` disabling zoom
-- `onPaste` with `preventDefault`
-- `transition: all`
-- `outline-none` without focus-visible replacement
-- Inline `onClick` navigation without `<a>`
-- `<div>` or `<span>` with click handlers (should be `<button>`)
-- Images without dimensions
-- Large arrays `.map()` without virtualization
-- Form inputs without labels
-- Icon buttons without `aria-label`
-- Hardcoded date/number formats (use `Intl.*`)
-- `autoFocus` without clear justification
-
-## Output Format
-
-Group by file. Use `file:line` format (VS Code clickable). Terse findings.
-
-```text
-## src/Button.tsx
-
-src/Button.tsx:42 - icon button missing aria-label
-src/Button.tsx:18 - input lacks label
-src/Button.tsx:55 - animation missing prefers-reduced-motion
-src/Button.tsx:67 - transition: all → list properties
-
-## src/Modal.tsx
-
-src/Modal.tsx:12 - missing overscroll-behavior: contain
-src/Modal.tsx:34 - "..." → "…"
-
-## src/Card.tsx
-
-✓ pass
-```
-
-State issue + location. Skip explanation unless fix non-obvious. No preamble.
diff --git a/dot_claude/empty_CLAUDE.md b/dot_claude/empty_CLAUDE.md
deleted file mode 100644
index e69de29..0000000
diff --git a/dot_claude/hooks/executable_cmem-to-obsidian.py b/dot_claude/hooks/executable_cmem-to-obsidian.py
deleted file mode 100644
index 5903563..0000000
--- a/dot_claude/hooks/executable_cmem-to-obsidian.py
+++ /dev/null
@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# Reads a Claude Code SessionEnd hook JSON on stdin and exports that session's
-# claude-mem learnings to a single Obsidian note. Stdlib only. Fails soft:
-# any error exits 0 without blocking the session.
-#
-# Data interface (discovered live, not guessed):
-#   - SQLite DB: ~/.claude-mem/claude-mem.db (read-only)
-#   - sdk_sessions.content_session_id == Claude Code session_id
-#   - sdk_sessions.memory_session_id  -> observations / session_summaries
-#   - observation types seen: discovery, change, feature, decision, bugfix, refactor
-#   - no private/excluded column exists: claude-mem drops <private> content at
-#     capture time so it never reaches the DB. We still scan defensively.
-#   - viewer deep link that resolves: http://localhost:<port>/?observation=<id>
-import sys, os, re, json, sqlite3, datetime
-from pathlib import Path
-
-HOME       = Path.home()
-DB_PATH    = Path(os.environ.get("CLAUDE_MEM_DB", HOME / ".claude-mem" / "claude-mem.db"))
-VAULT_DIR  = Path(os.environ.get("CMEM_OBSIDIAN_DIR", HOME / "Documents" / "Vault" / "90 - Archive" / "Learnings"))
-WORKER_PORT = os.environ.get("CLAUDE_MEM_WORKER_PORT", "37700")
-LOG_PATH   = HOME / ".claude" / "hooks" / "cmem-to-obsidian.log"
-
-# observation type -> note section
-SECTIONS = [
-    ("Decisions",        {"decision"}),
-    ("Fixes & gotchas",  {"bugfix"}),
-    ("Insights",         {"discovery", "feature", "change", "refactor"}),
-]
-
-
-def log(msg):
-    try:
-        with open(LOG_PATH, "a") as f:
-            f.write(f"{datetime.datetime.now().isoformat()} {msg}\n")
-    except Exception:
-        pass
-
-
-def slug(s):
-    return re.sub(r"[^a-z0-9]+", "-", (s or "").lower()).strip("-") or "unknown"
-
-
-def is_private(obs):
-    blob = " ".join(str(obs.get(k) or "") for k in ("title", "subtitle", "narrative", "text", "facts"))
-    return "<private>" in blob.lower()
-
-
-def connect_ro(path):
-    # read-only so we never lock or mutate the live DB / WAL
-    return sqlite3.connect(f"file:{path}?mode=ro", uri=True, timeout=5)
-
-
-def fetch(session_id):
-    con = connect_ro(DB_PATH)
-    con.row_factory = sqlite3.Row
-    cur = con.cursor()
-    row = cur.execute(
-        "SELECT memory_session_id, project, started_at FROM sdk_sessions "
-        "WHERE content_session_id = ? LIMIT 1", (session_id,)
-    ).fetchone()
-    if not row or not row["memory_session_id"]:
-        con.close()
-        return None
-    mem_id, project, started_at = row["memory_session_id"], row["project"], row["started_at"]
-
-    obs = [dict(r) for r in cur.execute(
-        "SELECT id, type, title, subtitle, narrative FROM observations "
-        "WHERE memory_session_id = ? ORDER BY created_at_epoch ASC", (mem_id,)
-    ).fetchall()]
-
-    summ = cur.execute(
-        "SELECT learned, completed, investigated, request FROM session_summaries "
-        "WHERE memory_session_id = ? ORDER BY created_at_epoch DESC LIMIT 1", (mem_id,)
-    ).fetchone()
-    con.close()
-    return {
-        "mem_id": mem_id,
-        "project": project or "unknown",
-        "started_at": started_at,
-        "observations": [o for o in obs if not is_private(o)],
-        "summary": dict(summ) if summ else {},
-    }
-
-
-def obs_link(oid):
-    return f"http://localhost:{WORKER_PORT}/?observation={oid}"
-
-
-def one_line(obs):
-    title = (obs.get("title") or "").strip()
-    sub = (obs.get("subtitle") or "").strip()
-    text = f"{title} — {sub}" if title and sub else (title or sub or "(untitled observation)")
-    return f"- {text} [cmem #{obs['id']}]({obs_link(obs['id'])})"
-
-
-def render_note(data, session_id):
-    project = data["project"]
-    pslug = slug(project)
-    # date from the session's own start time -> stable across re-runs (idempotent)
-    date = (data["started_at"] or datetime.datetime.now().isoformat())[:10]
-    short = session_id[:8]
-
-    summary = data["summary"]
-    abstract = (summary.get("learned") or summary.get("completed")
-                or summary.get("investigated") or summary.get("request") or "").strip()
-    abstract = re.sub(r"\s+", " ", abstract) or "No session summary recorded."
-
-    fm = [
-        "---",
-        f"date: {date}",
-        f"project: {project}",
-        f"session: {short}",
-        "source: claude-mem",
-        "tags:",
-        "  - claude-mem",
-        f"  - project/{pslug}",
-        "---",
-        "",
-        f"# {project} — Session Learnings ({date})",
-        "",
-        "> [!abstract] Session summary",
-        f"> {abstract}",
-        "",
-        f"Project: [[{project}]]",
-        "",
-    ]
-
-    body = []
-    by_id = {o["id"]: o for o in data["observations"]}
-    placed = set()
-    for heading, types in SECTIONS:
-        items = [o for o in data["observations"] if o["type"] in types]
-        if not items:
-            continue
-        body.append(f"## {heading}")
-        for o in items:
-            placed.add(o["id"])
-            if heading == "Decisions":
-                t = (o.get("title") or "").strip()
-                s = (o.get("subtitle") or "").strip()
-                body.append(f"- > [!note] {t}" + (f" — {s}" if s else "")
-                            + f" [cmem #{o['id']}]({obs_link(o['id'])})")
-            else:
-                body.append(one_line(o))
-        body.append("")
-
-    # any type we didn't map -> Insights catch-all
-    leftover = [o for o in data["observations"] if o["id"] not in placed]
-    if leftover:
-        body.append("## Insights")
-        body.extend(one_line(o) for o in leftover)
-        body.append("")
-
-    return "\n".join(fm + body).rstrip() + "\n", project, pslug, date, short
-
-
-def ensure_project_moc(project):
-    # so [[Project]] wikilink resolves
-    moc = VAULT_DIR / f"{project}.md"
-    try:
-        if not moc.exists():
-            moc.write_text(
-                f"---\ntags:\n  - moc\n  - project/{slug(project)}\n---\n\n# {project}\n\n"
-                "Map of content for claude-mem session learnings.\n"
-            )
-    except Exception as e:
-        log(f"moc write failed: {e}")
-
-
-def write_note(data, session_id):
-    text, project, pslug, date, short = render_note(data, session_id)
-    folder = VAULT_DIR / project
-    folder.mkdir(parents=True, exist_ok=True)
-    ensure_project_moc(project)
-    # deterministic filename keyed to session -> idempotent upsert
-    path = folder / f"{date} {project} {short}.md"
-    path.write_text(text)
-    log(f"wrote {path} ({len(data['observations'])} observations)")
-    return path
-
-
-def main():
-    try:
-        payload = json.load(sys.stdin)
-    except Exception:
-        return
-    session_id = payload.get("session_id")
-    if not session_id:
-        return
-    try:
-        if not DB_PATH.exists():
-            return
-        data = fetch(session_id)
-        if not data or not data["observations"]:
-            return
-        write_note(data, session_id)
-    except Exception as e:
-        log(f"export failed for session {session_id}: {e}")
-        return
-
-
-if __name__ == "__main__":
-    main()
diff --git a/dot_claude/hooks/executable_herdr-agent-state.sh b/dot_claude/hooks/executable_herdr-agent-state.sh
deleted file mode 100644
index cb5e840..0000000
--- a/dot_claude/hooks/executable_herdr-agent-state.sh
+++ /dev/null
@@ -1,101 +0,0 @@
-#!/bin/sh
-# installed by herdr
-# managed by herdr; reinstalling or updating the integration overwrites this file.
-# add custom hooks beside this file instead of editing it.
-# HERDR_INTEGRATION_ID=claude
-# HERDR_INTEGRATION_VERSION=7
-
-set -eu
-
-action="${1:-}"
-hook_input_file="$(mktemp "${TMPDIR:-/tmp}/herdr-claude-hook.XXXXXX")" || exit 0
-trap 'rm -f "$hook_input_file"' EXIT HUP INT TERM
-cat >"$hook_input_file" 2>/dev/null || true
-
-case "$action" in
-  session) ;;
-  *) exit 0 ;;
-esac
-
-[ "${HERDR_ENV:-}" = "1" ] || exit 0
-[ -n "${HERDR_SOCKET_PATH:-}" ] || exit 0
-[ -n "${HERDR_PANE_ID:-}" ] || exit 0
-command -v python3 >/dev/null 2>&1 || exit 0
-
-HERDR_ACTION="$action" HERDR_HOOK_INPUT_FILE="$hook_input_file" python3 - <<'PY'
-import json
-import os
-import random
-import socket
-import time
-
-source = "herdr:claude"
-action = os.environ.get("HERDR_ACTION", "")
-pane_id = os.environ.get("HERDR_PANE_ID")
-socket_path = os.environ.get("HERDR_SOCKET_PATH")
-hook_input_file = os.environ.get("HERDR_HOOK_INPUT_FILE")
-
-if not pane_id or not socket_path:
-    raise SystemExit(0)
-
-hook_input = {}
-if hook_input_file:
-    try:
-        with open(hook_input_file, encoding="utf-8") as handle:
-            content = handle.read()
-        if content.strip():
-            hook_input = json.loads(content)
-    except Exception:
-        hook_input = {}
-
-hook_event_name = str(hook_input.get("hook_event_name") or "")
-is_subagent = bool(hook_input.get("agent_id"))
-if is_subagent:
-    raise SystemExit(0)
-if hook_event_name == "SubagentStop":
-    # SubagentStop is a completion event. Older Herdr integrations mapped it
-    # to durable working, but Claude recap/away-summary can emit it after the
-    # main turn has already stopped. Never let it revive an idle pane.
-    raise SystemExit(0)
-request_id = f"{source}:{int(time.time() * 1000)}:{random.randrange(1_000_000):06d}"
-report_seq = time.time_ns()
-session_id = hook_input.get("session_id")
-agent_session_id = session_id if isinstance(session_id, str) and session_id else None
-transcript_path = hook_input.get("transcript_path")
-agent_session_path = transcript_path if isinstance(transcript_path, str) and transcript_path else None
-session_start_source = hook_input.get("source") if hook_event_name == "SessionStart" else None
-if not isinstance(session_start_source, str) or not session_start_source:
-    session_start_source = None
-if agent_session_id:
-    params = {
-        "pane_id": pane_id,
-        "source": source,
-        "agent": "claude",
-        "seq": report_seq,
-        "agent_session_id": agent_session_id,
-    }
-    if agent_session_path:
-        params["agent_session_path"] = agent_session_path
-    if session_start_source:
-        params["session_start_source"] = session_start_source
-    request = {
-        "id": request_id,
-        "method": "pane.report_agent_session",
-        "params": params,
-    }
-else:
-    raise SystemExit(0)
-
-try:
-    client = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM)
-    client.settimeout(0.5)
-    client.connect(socket_path)
-    client.sendall((json.dumps(request) + "\n").encode())
-    try:
-        client.recv(4096)
-    except Exception:
-        pass
-    client.close()
-except Exception:
-    pass
-PY
diff --git a/dot_claude/hooks/gitnexus/gitnexus-hook.cjs b/dot_claude/hooks/gitnexus/gitnexus-hook.cjs
deleted file mode 100644
index f6a4018..0000000
--- a/dot_claude/hooks/gitnexus/gitnexus-hook.cjs
+++ /dev/null
@@ -1,155 +0,0 @@
-#!/usr/bin/env node
-/**
- * GitNexus Claude Code Hook
- *
- * PreToolUse handler — intercepts Grep/Glob/Bash searches
- * and augments with graph context from the GitNexus index.
- *
- * NOTE: SessionStart hooks are broken on Windows (Claude Code bug).
- * Session context is injected via CLAUDE.md / skills instead.
- */
-
-const fs = require('fs');
-const path = require('path');
-const { execFileSync } = require('child_process');
-
-/**
- * Read JSON input from stdin synchronously.
- */
-function readInput() {
-  try {
-    const data = fs.readFileSync(0, 'utf-8');
-    return JSON.parse(data);
-  } catch {
-    return {};
-  }
-}
-
-/**
- * Check if a directory (or ancestor) has a .gitnexus index.
- */
-function findGitNexusIndex(startDir) {
-  let dir = startDir || process.cwd();
-  for (let i = 0; i < 5; i++) {
-    if (fs.existsSync(path.join(dir, '.gitnexus'))) {
-      return true;
-    }
-    const parent = path.dirname(dir);
-    if (parent === dir) break;
-    dir = parent;
-  }
-  return false;
-}
-
-/**
- * Extract search pattern from tool input.
- */
-function extractPattern(toolName, toolInput) {
-  if (toolName === 'Grep') {
-    return toolInput.pattern || null;
-  }
-
-  if (toolName === 'Glob') {
-    const raw = toolInput.pattern || '';
-    const match = raw.match(/[*\/]([a-zA-Z][a-zA-Z0-9_-]{2,})/);
-    return match ? match[1] : null;
-  }
-
-  if (toolName === 'Bash') {
-    const cmd = toolInput.command || '';
-    if (!/\brg\b|\bgrep\b/.test(cmd)) return null;
-
-    const tokens = cmd.split(/\s+/);
-    let foundCmd = false;
-    let skipNext = false;
-    const flagsWithValues = new Set(['-e', '-f', '-m', '-A', '-B', '-C', '-g', '--glob', '-t', '--type', '--include', '--exclude']);
-
-    for (const token of tokens) {
-      if (skipNext) { skipNext = false; continue; }
-      if (!foundCmd) {
-        if (/\brg$|\bgrep$/.test(token)) foundCmd = true;
-        continue;
-      }
-      if (token.startsWith('-')) {
-        if (flagsWithValues.has(token)) skipNext = true;
-        continue;
-      }
-      const cleaned = token.replace(/['"]/g, '');
-      return cleaned.length >= 3 ? cleaned : null;
-    }
-    return null;
-  }
-
-  return null;
-}
-
-function main() {
-  try {
-    const input = readInput();
-    const hookEvent = input.hook_event_name || '';
-
-    if (hookEvent !== 'PreToolUse') return;
-
-    const cwd = input.cwd || process.cwd();
-    if (!findGitNexusIndex(cwd)) return;
-
-    const toolName = input.tool_name || '';
-    const toolInput = input.tool_input || {};
-
-    if (toolName !== 'Grep' && toolName !== 'Glob' && toolName !== 'Bash') return;
-
-    const pattern = extractPattern(toolName, toolInput);
-    if (!pattern || pattern.length < 3) return;
-
-    // Resolve CLI path — try multiple strategies:
-    // 1. Relative path (works when script is inside npm package)
-    // 2. require.resolve (works when gitnexus is globally installed)
-    // 3. Fall back to npx (works when neither is available)
-    let cliPath = '/home/prad/.bun/install/global/node_modules/gitnexus/dist/cli/index.js';
-    if (!fs.existsSync(cliPath)) {
-      try {
-        cliPath = require.resolve('gitnexus/dist/cli/index.js');
-      } catch {
-        cliPath = ''; // will use npx fallback
-      }
-    }
-
-    // augment CLI writes result to stderr (KuzuDB's native module captures
-    // stdout fd at OS level, making it unusable in subprocess contexts).
-    const { spawnSync } = require('child_process');
-    let result = '';
-    try {
-      let child;
-      if (cliPath) {
-        child = spawnSync(
-          process.execPath,
-          [cliPath, 'augment', pattern],
-          { encoding: 'utf-8', timeout: 8000, cwd, stdio: ['pipe', 'pipe', 'pipe'] }
-        );
-      } else {
-        // npx fallback
-        const cmd = process.platform === 'win32' ? 'npx.cmd' : 'npx';
-        child = spawnSync(
-          cmd,
-          ['-y', 'gitnexus', 'augment', pattern],
-          { encoding: 'utf-8', timeout: 15000, cwd, stdio: ['pipe', 'pipe', 'pipe'] }
-        );
-      }
-      result = child.stderr || '';
-    } catch { /* graceful failure */ }
-
-    if (result && result.trim()) {
-      console.log(JSON.stringify({
-        hookSpecificOutput: {
-          hookEventName: 'PreToolUse',
-          additionalContext: result.trim()
-        }
-      }));
-    }
-  } catch (err) {
-    // Graceful failure — log to stderr for debugging
-    console.error('GitNexus hook error:', err.message);
-  }
-}
-
-main();
diff --git a/dot_claude/settings.json b/dot_claude/settings.json
deleted file mode 100644
index 13262cf..0000000
--- a/dot_claude/settings.json
+++ /dev/null
@@ -1,341 +0,0 @@
-{
-  "env": {
-    "CLAUDE_CODE_DISABLE_AUTO_MEMORY": "1",
-    "EDITOR": "/usr/bin/micro"
-  },
-  "permissions": {
-    "allow": [
-      "mcp__codegraph__codegraph_search",
-      "mcp__codegraph__codegraph_context",
-      "mcp__codegraph__codegraph_callers",
-      "mcp__codegraph__codegraph_callees",
-      "mcp__codegraph__codegraph_impact",
-      "mcp__codegraph__codegraph_node",
-      "mcp__codegraph__codegraph_status"
-    ],
-    "defaultMode": "auto"
-  },
-  "model": "fable",
-  "hooks": {
-    "Notification": [
-      {
-        "matcher": ".*",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "pixtuoid-hook"
-          }
-        ]
-      }
-    ],
-    "PermissionRequest": [
-      {
-        "matcher": "*",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "if [ -x '/home/prad/.orca/agent-hooks/claude-hook.sh' ]; then /bin/sh '/home/prad/.orca/agent-hooks/claude-hook.sh'; fi"
-          }
-        ]
-      }
-    ],
-    "PostToolUse": [
-      {
-        "matcher": "*",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "if [ -x '/home/prad/.orca/agent-hooks/claude-hook.sh' ]; then /bin/sh '/home/prad/.orca/agent-hooks/claude-hook.sh'; fi"
-          }
-        ]
-      },
-      {
-        "matcher": ".*",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "pixtuoid-hook"
-          }
-        ]
-      },
-      {
-        "matcher": "Bash",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "atuin hook claude-code"
-          }
-        ]
-      }
-    ],
-    "PostToolUseFailure": [
-      {
-        "matcher": "*",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "if [ -x '/home/prad/.orca/agent-hooks/claude-hook.sh' ]; then /bin/sh '/home/prad/.orca/agent-hooks/claude-hook.sh'; fi"
-          }
-        ]
-      },
-      {
-        "matcher": "Bash",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "atuin hook claude-code"
-          }
-        ]
-      }
-    ],
-    "PreToolUse": [
-      {
-        "matcher": "*",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "if [ -x '/home/prad/.orca/agent-hooks/claude-hook.sh' ]; then /bin/sh '/home/prad/.orca/agent-hooks/claude-hook.sh'; fi"
-          }
-        ]
-      },
-      {
-        "matcher": ".*",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "pixtuoid-hook"
-          }
-        ]
-      },
-      {
-        "matcher": "Bash",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "atuin hook claude-code"
-          }
-        ]
-      }
-    ],
-    "SessionEnd": [
-      {
-        "hooks": [
-          {
-            "type": "command",
-            "command": "python3 '/home/prad/.claude/hooks/cmem-to-obsidian.py'",
-            "timeout": 15
-          }
-        ]
-      },
-      {
-        "matcher": ".*",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "pixtuoid-hook"
-          }
-        ]
-      }
-    ],
-    "SessionStart": [
-      {
-        "matcher": ".*",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "pixtuoid-hook"
-          }
-        ]
-      },
-      {
-        "matcher": "^(startup|resume|clear|compact|fork)$",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "bash '/home/prad/.claude/hooks/herdr-agent-state.sh' session",
-            "timeout": 10
-          }
-        ]
-      }
-    ],
-    "Stop": [
-      {
-        "hooks": [
-          {
-            "type": "command",
-            "command": "if [ -x '/home/prad/.orca/agent-hooks/claude-hook.sh' ]; then /bin/sh '/home/prad/.orca/agent-hooks/claude-hook.sh'; fi"
-          }
-        ]
-      }
-    ],
-    "StopFailure": [
-      {
-        "hooks": [
-          {
-            "type": "command",
-            "command": "if [ -x '/home/prad/.orca/agent-hooks/claude-hook.sh' ]; then /bin/sh '/home/prad/.orca/agent-hooks/claude-hook.sh'; fi"
-          }
-        ]
-      }
-    ],
-    "SubagentStart": [
-      {
-        "matcher": ".*",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "pixtuoid-hook"
-          }
-        ]
-      },
-      {
-        "matcher": "tldraw-offline",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "sh '/home/prad/skills/tldraw-offline/inject-server-context.sh' SubagentStart"
-          }
-        ]
-      }
-    ],
-    "SubagentStop": [
-      {
-        "matcher": ".*",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "pixtuoid-hook"
-          }
-        ]
-      }
-    ],
-    "UserPromptSubmit": [
-      {
-        "hooks": [
-          {
-            "type": "command",
-            "command": "if [ -x '/home/prad/.orca/agent-hooks/claude-hook.sh' ]; then /bin/sh '/home/prad/.orca/agent-hooks/claude-hook.sh'; fi"
-          }
-        ]
-      }
-    ]
-  },
-  "enabledPlugins": {
-    "caveman@caveman": true,
-    "claude-mem@thedotmack": true,
-    "context-mode@context-mode": true,
-    "context7@claude-plugins-official": false,
-    "council@council-of-high-intelligence": true,
-    "exa@claude-plugins-official": true,
-    "frontend-design@claude-plugins-official": true,
-    "gopls-lsp@claude-plugins-official": true,
-    "gopls@claude-code-lsps": true,
-    "lua-lsp@claude-plugins-official": true,
-    "ponytail@ponytail": true,
-    "solidity-language-server@claude-code-lsps": true,
-    "understand-anything@understand-anything": true,
-    "vtsls@claude-code-lsps": true,
-    "yaml-lsp@zircote-lsp": true,
-    "diagram-design@diagram-design": true
-  },
-  "extraKnownMarketplaces": {
-    "caveman": {
-      "source": {
-        "source": "github",
-        "repo": "JuliusBrussee/caveman"
-      }
-    },
-    "claude-code-lsps": {
-      "source": {
-        "source": "github",
-        "repo": "Piebald-AI/claude-code-lsps"
-      }
-    },
-    "claude-plugins-official": {
-      "source": {
-        "source": "github",
-        "repo": "anthropics/claude-plugins-official"
-      }
-    },
-    "council-of-high-intelligence": {
-      "source": {
-        "source": "github",
-        "repo": "0xNyk/council-of-high-intelligence"
-      }
-    },
-    "mempalace": {
-      "source": {
-        "source": "github",
-        "repo": "MemPalace/mempalace"
-      }
-    },
-    "omc": {
-      "source": {
-        "source": "git",
-        "url": "https://github.com/Yeachan-Heo/oh-my-claudecode.git"
-      }
-    },
-    "ponytail": {
-      "source": {
-        "source": "github",
-        "repo": "DietrichGebert/ponytail"
-      }
-    },
-    "thedotmack": {
-      "source": {
-        "source": "github",
-        "repo": "thedotmack/claude-mem"
-      }
-    },
-    "understand-anything": {
-      "source": {
-        "source": "github",
-        "repo": "Egonex-AI/Understand-Anything"
-      }
-    },
-    "zircote-lsp": {
-      "source": {
-        "source": "github",
-        "repo": "zircote/lsp-marketplace"
-      }
-    },
-    "diagram-design": {
-      "source": {
-        "source": "github",
-        "repo": "cathrynlavery/diagram-design"
-      }
-    }
-  },
-  "tui": "fullscreen",
-  "skipDangerousModePermissionPrompt": true,
-  "agentPushNotifEnabled": true,
-  "skipAutoPermissionPrompt": true,
-  "autoMode": {
-    "environment": [
-      "### Org-wide",
-      "**Organization**: None configured",
-      "**Cloud provider(s)**: None configured",
-      "**Repository visibility**: Private — prdlk/leetcode (github.com)",
-      "**Internal sharing / snippet hosting**: None configured — treat public paste/gist services as outside the trust boundary",
-      "**Secrets management**: None configured",
-      "**Default / protected branches**: Default branch `main`; no protected branches listed (rulesets not queryable here)",
-      "**CI/CD deploy targets**: None configured",
-      "**Network posture**: None configured",
-      "**Source control**: The trusted repo (prdlk/leetcode on github.com) and its remote(s) only — no additional orgs configured",
-      "**Trusted internal domains**: None configured",
-      "**Trusted cloud buckets**: None configured",
-      "**Key internal services**: None configured",
-      "**Internal package registry**: None configured",
-      "**Sensitive data locations & audiences**: any file or store holding personal data, confidential business data, credentials, regulated data, or similarly sensitive material; preserve exact handles when known and share only with audiences cleared at the [named+specifics] bar. Note: `.env*` patterns are gitignored in this repo (`.env`, `.env.local`, `.env.development.local`, `.env.test.local`, `.env.production.local`) — treat matching files as sensitive.",
-      "**Data retention / declassification**: None configured",
-      "**Sensitive remote targets**: any namespace, host, or container whose name carries `prod` or `production` as a whole word or name segment (hyphen/underscore/dot-delimited — e.g. matches `prod-db`, not `producer`)",
-      "**Protected deployment namespaces / environments**: None configured — fall back to the Sensitive remote targets heuristic",
-      "**Protected IaC scopes**: IAM, RBAC, networking, quota, and node-pool resources; anything whose name or tag carries `prod` or `production` as a whole word or name segment",
-      "### User-specific",
-      "**Primary use of Claude Code**: software development (personal — Leetcode solutions/notes repo)",
-      "**Trusted repo**: prdlk/leetcode (github.com), private — the working directory the agent started in and its configured remote `origin`. As a private repo, confidential material may be committed here, but secrets/credentials are never cleared into it by visibility alone.",
-      "**Org-specific CLIs**: None configured",
-      "routine actions under `prdlk/leetcode` (this repo) treated as low-risk personal-project work"
-    ]
-  }
-}