The cli-checks matrix hardcoded the six shipped portals, so a CLI
scaffolded by /add-portal in a fork shipped typecheck and test scripts
that fork CI never ran - while security_guards.py already globs
.agents/**/package.json and covers new portals automatically. A
discover-clis job now emits the matrix from
.agents/skills/*/cli/package.json; on upstream it resolves to the same
six portals, and a fork-added portal joins the matrix with no workflow
edit. /add-portal's Register step now says so.
* test(cli): pin the 429/5xx retry contract in all six portal CLIs
The portal-skill contract requires backoff on 429/5xx, and every CLI
implements it - a retry loop with exponential delay and jitter - but
nothing verified the loops actually retry, stop retrying on plain
4xx, or give up after the documented attempt budget. A regression
here is invisible: a CLI that stops retrying still works on every
healthy request.
Each CLI gains tests/retry-backoff.test.ts, network-free, using the
request-timeout.test.ts pattern from #197 (import the fetch wrapper,
stub globalThis.fetch): a stubbed fetch counts attempts, and a
stubbed setTimeout fires immediately so the exhaustion case does not
sleep through the real 500ms -> 5s/8s backoff schedule (tests run in
milliseconds, not ~17s).
Three assertions per fetch wrapper, adapted to each CLI's documented
semantics:
- a 429 is retried and the next attempt's result is returned
- a plain 4xx is not retried (jobbank's fetchWithUA RETURNS the
response for callers to handle - pinned as such; linkedin's
htmlFetch returns "" on 404; freehire's apiGet returns null)
- persistent 5xx gives up after the initial attempt plus six
retries (7 fetch calls) with the status in the error
freehire additionally pins its documented graceful-degradation
contract: a connection failure fails fast with no retry. jobdanmark
exercises both apiFetch and apiPost, which carry separate copies of
the loop that could drift apart.
Mutation-checked: changing maxRetries in jobindex makes the
exhaustion test fail, so the tests distinguish the current behavior
from a silently altered one.
Verified: bun test green in all six CLIs (jobindex 19, jobnet 20,
jobbank 20, jobdanmark 21, linkedin 21, freehire 31 - 0 fail);
tsc --noEmit clean in all six; python3 tools/lint_skills.py OK.
* test(jobindex): pin apiFetch's retry loop alongside htmlFetch's
Review parity gap: jobindex carries two separate copies of the retry
loop and only htmlFetch was exercised, so apiFetch's retry budget
could drift silently - the same situation jobdanmark's test already
handles for its apiFetch/apiPost pair.
apiFetch gets the same three assertions, adapted to its documented
semantics (JSON return on success, throw on plain 4xx): a 429 is
retried and the next attempt's parsed body returned, a 400 is not
retried, persistent 5xx gives up after the initial attempt plus six
retries (7 calls).
Mutation-checked on the new axis: changing apiFetch's maxRetries
(the file's first copy of the loop) fails its exhaustion test while
htmlFetch's tests stay green, so each wrapper is now pinned
independently.
Verified: bun test 30 pass / 0 fail (full jobindex suite);
tsc --noEmit clean.
Adds Step 4.75 to /scrape: detects the failure mode where a portal changes markup and its parser exits 0 with zero or garbled results (invisible to the Step 1c fallback, which only fires on non-zero exit). Free pass over this run's results (degraded scan) plus seen_jobs.json yield history; bounded escalation on suspicion only (the portal's own SKILL.md test query, one broader retry, rate-limit never treated as evidence); health: lines in the Step 5 summary with a confirmation-gated enabled:false quarantine offer; healthy portals stay silent. Adds a /scrape health [portal] probe-only mode. Persists a portal field in seen_jobs.json additively (per the /rank precedent), with read-time URL-domain attribution for pre-field entries so no migration is needed.
Folded into /scrape rather than a standalone /doctor command - the detection lives where the evidence (run results + yield history) already is, and a routine command catches rot a user would otherwise notice weeks late. By @ayobamiseun.
Adds Step 2b to /outcome: surfaces open applications gone quiet (default 10 days), drafts a brief channel-appropriate follow-up in the candidate's voice using only claims from the already-submitted materials, and logs it (followed up marker in notes + followup_YYYY-MM-DD.md in the archive). Reachable from the no-arg pipeline table (now showing days-quiet and follow-ups-sent) and via /outcome followup [N|company]. Draft-only never send, capped at two follow-ups terminating into Step 2's existing no_response path, and a thank-you note offered the moment Step 3 records a completed interview stage. Reads the contact_person column nothing previously consumed.
Folded into /outcome rather than a standalone command - dependency-free (unlike /gmail-sync) and reusing detection, the archive, the notes ledger, and the resolution path already there. The invited return of #46 (closed stale, not on merit). Guardrail tests mirror the /notion-sync pattern; 10-vs-30-day threshold contrast with /gmail-sync documented and test-pinned.
By @ayobamiseun.
Bare z.coerce.number() accepted negative and fractional values for count/pagination flags, and slice(0, limit) with a negative limit silently dropped trailing results instead of erroring. Tightens the schemas to .int().min(1) across all four Danish portal CLIs (including jobnet occupations --per-page) with network-free validation tests.
By @ayobamiseun.
Extend the offline CLI contract tests to the two remaining Danish
portal CLIs. Both implement the documented error contract (JSON
errors on stderr, exit 1) but had no test locking it in:
- jobindex-search: search without --query, detail without an ID,
and bunli numeric-option validation (--page not-a-number)
- jobnet-search: detail without an ID, occupations without
--search-string, suggestions without --query, and numeric-option
validation
All asserted paths exit before any network request, matching the
no-live-portal-requests CI policy. Assertions were written against
observed CLI output, not assumed shapes.
Jobbank and Jobdanmark each had only one narrow test, leaving required-argument errors, RSS normalization, JSON-LD variants, and malformed-page handling unprotected.
Add network-free fixture and subprocess tests for repeated RSS filters, description and ID parsing, stderr JSON errors, Bunli numeric validation, JSON-LD objects and arrays, optional fields, not-found pages, and parse failures.
The suites now cover eight Jobbank cases and six Jobdanmark cases without making live portal requests.
Valid JSON such as [] or {"permissions": []} caused lint_skills.py to raise AttributeError because it assumed both values were objects.
Validate the top-level settings value and permissions object before reading nested keys. Malformed settings now produce clear lint errors and exit 1 without a traceback.
Add subprocess regression tests covering invalid JSON, malformed root values, invalid permissions values, and non-list permissions.allow values.
* ci: run the Python test suite - CONTRIBUTING.md asks for tests CI never executes
CONTRIBUTING.md tells contributors to put Python tool tests in tests/
and run the relevant suites, and tests/ now holds real ones
(test_salary_lookup.py, test_convert_salary_excel.py from #75) - but no
CI job executes them. A suite that never runs in CI can't gate a PR and
silently rots. New python-tests job: unittest discover over tests/,
stdlib only, no new dependencies. Future test files run without any
workflow change.
Also lands tests/test_security_guards.py, which missed #84's merge
window (pushed to the branch as #84 was being merged; the merge took
2a6cb8c, the tests were 260c37a). 13 unittest cases in the existing
tests/ style: each copies the guard script into a synthetic repo tree
and runs it as a subprocess - the same way CI invokes it - asserting
real exit codes and messages. Every forbidden state fails (Bash(*) and
Bash(curl:*) additions, each personal-data gitignore rule removed one
at a time, each forbidden lifecycle script, trustedDependencies,
invalid settings JSON, zero manifests); every non-event passes (dropped
shipped permission, extra ignore rules, benign scripts, hostile
manifest inside node_modules); and the real repo passes its own guards.
22 tests total, all passing locally via the exact command the job runs.
* test: use benign lifecycle-script values in fixtures - AV heuristics flag attack-shaped strings
Review found the curl-pipe-to-sh fixture value matches a real Defender
signature (Trojan:Script/Stealer.HAX!MTB): Windows quarantines the temp
package.json mid-test, making the suite flaky for any Windows
contributor who runs it - while proving nothing extra, since the guard
flags the script KEY and never inspects the value.
Fixture values are now 'echo test' (also in the node_modules-ignored
test, same class of string), with a comment on the key-only test
explaining why the value must stay benign so a future 'make the fixture
realistic' cleanup doesn't reintroduce the quarantine flake. Coverage
is unchanged: same keys, same assertions, 13 tests passing.
GitHub auto-links #N only in issue/PR comments and commit messages, not
in rendered markdown files - so all 26 precedent references in
CONTRIBUTING.md ((#30), (#55, #56), ...) render as plain text, and the
reader can't jump to the precedent being cited.
Converted every bare #N to a reference-style link ([#N] in prose, URL
definitions collected at the bottom of the file). Definitions use the
/issues/N form, which GitHub redirects to /pull/N when the number is a
PR, so each link resolves correctly whether it points at an issue or a
pull request. No prose changed; existing inline links (the Discussions
URLs) untouched.
* ci: add supply-chain guards - permission allowlist, gitignore rules, manifest checks, pinned actions
This template's threat model is unusual: it ships pre-approved Claude Code
permissions (.claude/settings.json) and CLI code that every fork user
executes via those permissions. A plausible-looking PR could therefore
ship risk to every forker: widen a permission to Bash(*), weaken the
personal-data gitignore rules, or smuggle code execution into bun install
via a lifecycle script. Nothing checked for these mechanically.
New job security-guards runs tools/security_guards.py (stdlib only):
- settings.json: every permissions.allow entry must be in an exact,
in-repo allowlist. The guard makes permission changes loud, not
impossible - a PR that intentionally widens permissions must update
the allowlist in the same diff, so the widening is explicit and
reviewable
- .gitignore: the personal-data rules (tracker, documents/**, cv/main_*,
salary data, seen_jobs) must all still be present - the mirror image
of the placeholder-integrity job
- .agents/**/package.json: no lifecycle scripts (preinstall/install/
postinstall/prepare/prepack) and no trustedDependencies, which would
execute arbitrary code during bun install on users' machines
New job dependency-review (PRs only): actions/dependency-review-action
flags newly introduced vulnerable or malicious dependencies,
fail-on-severity high.
Workflow hardening: explicit top-level permissions: contents: read
(least-privilege token), and all actions pinned to commit SHAs resolved
from the same major tags already in use (checkout v4, setup-python v5,
setup-bun v2), with the tag recorded in a comment.
Honest limit, recorded in the workflow header: a PR can edit this
workflow itself, so these guards catch accidents and casual attempts,
not a determined author. Branch protection with required checks and
human review of workflow/settings diffs remain the real backstop.
Verified locally: positive run passes; injecting Bash(*) into
settings.json, deleting the tracker gitignore rule, and adding a
postinstall script each fail the guard with the intended message, and
reverting restores a clean pass.
* ci: scope dependency-review to upstream PRs - forks lack Dependency graph by default
Verified on a fork: the action fails with 'Dependency review is not
supported on this repository' until Dependency graph is manually enabled,
and forks don't inherit it. Guarded with the same
github.repository == upstream condition the other upstream-only jobs use.
With the graph enabled the action passes, so the config itself is sound.
* ci: probe Dependency graph before dependency-review - warn and pass when unavailable
The upstream PR run showed Dependency graph is disabled on the upstream
repo too (the action hard-fails: 'Dependency review is not supported on
this repository'), not just on forks. Only the repo owner can enable it,
so a hard red X here is friction, not signal.
The job now probes the dependency-graph SBOM endpoint with the workflow
token first: HTTP 200 runs the real review; anything else emits a
::warning:: naming the setting to flip (Settings -> Advanced Security ->
Dependency graph) and passes. Same graceful-skip pattern the workflow
uses for optional tools - the check self-activates the moment the graph
is enabled, no workflow change needed.
Every PR to this repo is currently verified by hand. This adds the checks
a machine can do:
- latex-smoke: compiles cv/main_example.tex (lualatex) and the new
cover_letters/cover_example.tex (xelatex) in the texlive/texlive
container, failing on any LaTeX error. Exact page-count assertions
(CV=2, cover letter=1) run on the upstream repo only
- lint (tools/lint_skills.py, also runnable locally): every SKILL.md has
parseable YAML frontmatter with name+description (frontmatter breakage
happened before - 37a0eed), allowed-tools 'bun run <path>' targets
exist, command files start with a '# /<name>' title, settings.json is
valid JSON with a permissions.allow list
- cli-typecheck: bun install + tsc --noEmit for all five portal CLIs
(matrix, fail-fast off)
- placeholder-integrity (upstream only): tracked template files still
carry their placeholder tokens, catching accidental personal-data
commits before they land
Fork-friendly by design: /setup personalizes CLAUDE.md, the skill files,
and main_example.tex in forks, so placeholder checks and exact page
counts are guarded with github.repository == upstream; compile success
and lint run everywhere. Live CLI smoke tests are deliberately excluded:
network-flaky, and linkedin-search is personal-use-only per its own ToS
warning - CI-automated requests would violate it. CLIs are typechecked
instead.
The cover letter previously had no tracked example (cover_*.tex is
gitignored), so cover_example.tex is new: a placeholder letter following
the documented 06 structure, demonstrating the correct itemize-outside-
lettercontent pattern. It doubles as the structural reference /apply
Step 2 looks for on fresh clones, which until now matched nothing. The
gitignore exception is ordered after Cover_*.tex because case-insensitive
filesystems match that pattern against cover_example.tex too.
Writing it surfaced a latent bug in the documented template itself:
06-cover-letter-templates.md's structure ends with \closing{Kind
regards,\} - but cover.cls appends its own \, and the doubled break
produces '! LaTeX Error: There's no line here to end.' on every compile
(nonstopmode swallows it, so it went unnoticed). Fixed in 06 and noted
in the example.
07-interview-prep.md holds STAR examples, tough-question patterns,
questions to ask, and a roleplay protocol - and the job-application-
assistant skill names interview preparation as its Step 4 - but no
command operationalizes any of it. /apply ends at 'files ready', and the
moment an interview is scheduled, nothing picks the thread back up.
/interview does, drawing on the archive /outcome now maintains.
/apply optimizes what the company reads; /interview optimizes what the
company hears. The bridge is consistency: the interviewer read the
submitted CV and cover letter, so prep must match what they claim.
How it works:
- Loads the application context from documents/applications/
<company>_<role>/: the exact posting, the submitted drafts, and
outcome.md's stage + recorded feedback (stage-N feedback is the
highest-priority input for stage-N+1 prep). Graceful fallbacks for
applications that predate /outcome, stating plainly what is missing
- Runs the Company Research Checklist that 04-job-evaluation.md defines
but nothing executes, plus interviewer-angle notes from public
professional info only. Every company claim is independently verified
before it enters the pack - same rule as cover-letter claims
- Builds a stage-specific prep pack: likely questions (earlier-stage
feedback first, then fit-evaluation gaps with honest bridge answers
per 07's you-don't-have-X pattern, then posting requirements, then
stage type), STAR mapping via 07's Use-for tags with new drafts
grounded strictly in profile facts, a consistency brief of the
submitted documents' probeable claims, customized tough questions,
4-6 questions to ask, logistics tips
- Saves the pack to documents/applications/<company>_<role>/
interview_prep_<stage>.md - one per stage, kept as history,
gitignored with the rest of the archive
- Offers a mock interview following 07's Roleplay Guidelines verbatim,
with feedback calibrated against the behavioral profile (same
voice-consistency rule the /apply reviewer applies)
- Never edits framework or profile files, except appending
user-approved STAR examples to 07 on explicit request
Integration: /outcome suggests /interview when an interview stage is
recorded; documents/README.md documents the interview_prep_<stage>.md
files (and that /setup ignores them); README commands list and file
tree.
/setup Path A already mines documents/applications/<company>_<role>/
(job_posting.md, submitted drafts, outcome.md) to calibrate
04-job-evaluation.md and surface STAR candidates - but nothing in the
workflow systematically writes those folders, so the calibration machinery
only runs for users who hand-maintain the archive. /outcome closes the
loop: it writes the data /setup reads.
How it works:
- Identifies the application from job_search_tracker.csv (by argument, or
by listing open applications); applications made outside the workflow
get a new tracker row
- Records progress updates (interview stages, offers) and resolutions
using the exact status enum documents/README.md documents, plus one
additive value: in_progress, for open applications between updates.
/setup's calibration only draws conclusions from final statuses
- Archives the submitted cv_draft.tex / cover_letter.tex (copy, never
move; existing archived files are never overwritten - the archive is
what was actually submitted) and fetches job_posting.md from the
tracker's source URL while it is still alive; a dead URL gets a
user-pasted copy or an explicit unavailable stub, never a
reconstruction
- Updates the tracker row's status and notes; never restructures the CSV
- After 3+ resolved outcomes (or a repeating pattern), points the user
back to /setup Path A - /outcome writes data, /setup interprets it,
and this command never edits framework or profile files itself
- Idempotent: re-running appends stages and dated notes, never
duplicates folders, rows, or history
Also aligns the outcome.md status enum across docs: setup.md Step A3
listed hired/rejected/no_response/interview_only while documents/README.md
already had offer_declined; both now carry the full enum including
in_progress. documents/applications/** and the tracker are already
gitignored, so all recorded data stays personal.
Docs: README (commands list, file tree), documents/README.md (/outcome
cross-reference and in_progress semantics), one-line handoff at the end
of /apply Step 6.
/scrape finds and dedupes postings; /apply evaluates one at a time in
depth. Nothing connects the two ends: after a scrape returns 20 jobs, the
user eyeballs a table to decide where to spend /apply effort. /rank is the
bridge: batch-score every new posting against the fit framework and return
a ranked shortlist.
How it works:
- Selects jobs with status "new" from job_scraper/seen_jobs.json (--all
re-ranks everything unapplied; a focus argument filters), excluding
anything already in job_search_tracker.csv
- Dispatches parallel general-purpose agents (~5 jobs each) that WebFetch
each posting and score the five dimensions from 04-job-evaluation.md.
The rubric (skill match areas, career goals, deal-breakers) is passed
inline per the same token-efficiency rules /apply uses; agents score
only from actually fetched content and mark dead postings expired,
never guessing from a title
- Triage depth by design: posting text vs. profile only - no company
research, no salary lookups. /apply's Step 1 evaluation stays
authoritative and always re-runs on handoff
- Aggregates with the framework's 30/25/15/30 weighting and verdict
bands; location deal-breakers veto regardless of score; deadlines
within 7 days get urgency flags and win ties
- Updates seen_jobs.json additively (status "ranked"/"expired" plus
rank_score/rank_verdict/rank_date) so /scrape dedup keeps working;
the tracker is read-only. Re-running is idempotent
Integration: job-scraper SKILL.md documents the new status values and
suggests /rank after large scrape batches; README (commands list, file
tree, quick-start step 4).
An ATS reads the compiled PDF's embedded text layer, not the rendered page,
and LaTeX can silently produce PDFs whose text extracts as garbage: icon
glyphs where contact details should be, (cid:*) markers from fonts without
Unicode mappings, interleaved lines from multi-column layouts. This matters
more now that /add-template lets users bring arbitrary templates. The
existing Step 5 loop verifies what a human sees; this adds verification of
what a parser sees.
New Step 5d in /apply (CV only - cover letters rarely go through keyword
screening; cleanup renumbered to 5e):
- Extract the CV PDF's text layer with pdftotext -layout. pdftotext
(poppler) is an optional dependency: if missing, the mechanical check is
skipped with a warning and keyword coverage falls back to the visual PDF
read - the same graceful-skip pattern as salary_lookup.py
- Parseability checks verified against a real extraction of the stock
template: email/phone must survive as literal text (fontawesome icons
extract as harmless glyph-name noise like MOBILE-ALT/Envelope, but a
contact detail carried only by an icon or hyperlink is invisible to ATS),
no (cid:*) or replacement-character garbage, reading order matching
visual order, dates present
- Keyword coverage reuses the required/preferred list from Step 1, matched
in the posting's language, reported as covered / synonym-only /
missing-have-it / missing-gap. Honesty rule enforced: keywords the
profile genuinely supports get added to experience bullets; genuine gaps
stay visible, never stuffed
Integration: CLAUDE.md verification checklist section, ATS Parseability
guidance in 05-cv-templates.md, narrow Bash(pdftotext:*) entry in the
pre-approved permissions (keeping with the tightened scope from #27),
cv/*.txt gitignored (extraction is personal data; also deleted by the
step itself), and optional-dependency docs in README and SETUP.
The README has always invited users outside Denmark to build equivalents of
the four Danish portal CLI skills, but doing so meant reverse-engineering
.agents/skills/*/cli/ by hand. /add-portal turns that invitation into a
guided workflow:
- Interviews the user for the portal URL, skill name, market/language
(trigger phrases in the local language, like the Danish skills), and a
realistic test query
- Investigates the portal before writing code: search-URL pattern, result
structure (JSON API preferred over HTML), detail-page pattern, robots.txt
and access rules. Auth-walled portals are declined; portals with
restrictive terms get a prominent personal-use-only warning in the
generated SKILL.md (same as linkedin-search)
- Scaffolds from the canonical structure with linkedin-search as the
zero-dependency reference, enforcing the shared portal-skill contract:
search/detail commands, common flags, {meta, results} JSON shape, stderr
JSON errors, backoff on 429/5xx, chunked parsing
- Mandatory live test-run (search + detail + test suite) before registering
- Optionally wires the portal into /scrape via search-queries.md
The generator is country-agnostic; its output is market-specific and stays
in the user's fork, matching the repo policy that upstream remains a
universal template.
Docs: README (commands list, file structure, Job search tools section) and
SETUP.md (CLI install section pointer).
Users could already swap the stock moderncv/cover.cls templates, but only by
hand-editing the guidance in 05-cv-templates.md and 06-cover-letter-templates.md.
/add-template automates that:
- Interviews the user for the template's instructions: compile engine, fonts
(bundled files or system), style rules to preserve, and hard page limit
- Stores the template profile-agnostic ([PLACEHOLDER] tokens) under templates/
with a TEMPLATE.md manifest, so templates are safe to commit and share
- Runs a mandatory test compile with dummy data before registering anything
- Activates via a single managed block in 05/06, which /apply already reads,
so no changes to the /apply workflow are needed; --use default is a clean
revert to the stock templates
- --list and --use <name> manage multiple registered templates
Docs: README (commands list, file structure, LaTeX templates section) and
SETUP.md (compile section pointer).
Ayobami Adegoke