6d5d111faf
feat(skills): land four-vendor skill corpus ( #803 )
...
## Summary
- Lands the AgentOps skill corpus across source and Codex wrappers,
including Gemini image targets.
- Integrates the skill branch onto current origin/main and refreshes
generated manifests/catalogs.
- Normalizes local next-work queue enum drift and fixes shellcheck in
alias-collision validation.
## Validation
- bash scripts/regen-all.sh --check
- bash scripts/validate-skill-schema.sh
- bash tests/skills/test-token-budgets.sh
- bash tests/skills/run-all.sh
- bash scripts/audit-codex-parity.sh && bash
scripts/validate-codex-override-coverage.sh && bash
scripts/validate-codex-generated-artifacts.sh --scope worktree && bash
scripts/validate-codex-api-conformance.sh && bash
scripts/validate-codex-runtime-sections.sh && bash
scripts/lint-codex-native.sh
- bash skills/heal-skill/scripts/heal.sh --strict
- PRE_PUSH_SKIP_MKDOCS=1 bash scripts/pre-push-gate.sh --fast
MkDocs strict remains skipped locally via the documented
PRE_PUSH_SKIP_MKDOCS=1 override because the repo currently emits
repo-wide strict-link warnings unrelated to this landing; CI remains
authoritative.
2026-06-06 23:44:42 -04:00
b742175341
feat(complexity): executable acceptance for the refactor-hotspot finder (soc-cve7s #complexity-hexagon) ( #444 )
...
soc-qk4b skill-hexagon-crank — peripheral skill. /complexity (domain,
consumes doc + standards) lacked a .feature.
- skills/complexity/references/complexity.feature (NEW): rank by
cyclomatic complexity; no-path → recent changes; focused hotspot list
- added Reference Documents section; registry regenerated
consumes [doc, standards] already filled — acceptance-only.
How tested: lint-skills ✓ complexity (214 lines); scenarios --lint 0
errors; codex parity passed; registry up to date.
Sibling: acceptance-only crank like /design #443 .
NOTE: claude-review infra-red (weekly limit, resets May 25) —
operator-authorized bypass when sole red.
Closes-scenario: soc-cve7s#complexity-hexagon
Bounded-context: BC4-Validation
Evidence: skills/complexity/references/complexity.feature
2026-05-23 03:18:49 -04:00
8c731aef64
fix(ci): make skill validate-contracts billboard-aware (clears 4 CI failures)
...
#275 's billboard refactor thinned process-skill SKILL.md files and moved
detail into references/, but the validate contracts still grepped SKILL.md.
skill-lint + smoke-test: relax content-presence checks in crank/implement/
post-mortem/swarm validate.sh to scan the skill as a unit (SKILL.md +
references/); structural/identity checks stay SKILL.md-only. test-first-smoke
updated to match relocated SPEC/TEST WAVE + Step 0/4 headings.
skill-lint line caps: trim flywheel 310 -> 286 (cap 300), using-agentops
261 -> 239 (cap 250) by removing redundant prose, no content lost.
skill-integrity: link 3 orphaned references (crank/branch-isolation,
validation/flags + release-readiness-gates).
codex parity: regenerate stale skills-codex source hashes (77 skills).
Local: run-all.sh PASS, heal.sh --strict clean, smoke-test PASS.
2026-05-15 16:30:32 -04:00
00f178671a
feat(practice): backfill practices: declarations into 13 next-batch skills (pass 2)
...
Adds practices: frontmatter to: research, council, complexity, bug-hunt,
standards, goals, brainstorm, design, forge, harvest, knowledge-activation,
retro, pre-mortem.
scripts/validate-practice-citations.sh report:
primitives scanned: 754
with practices field: 26 (was 13)
missing practices field: 728 (was 741)
invalid slug citations: 0
Also untracks .agents/ session artifacts that pass-1 incorrectly committed
outside the audit-truth allowlist (scripts/check-no-tracked-agents.sh). The
session-artifact files (research/plans/council/post-mortems/learnings/rpi
execution packets) are intended to be local-only per the contract; only
.agents/rpi/next-work.jsonl is allowlisted. Fixes the pre-push gate's
'.agents/ write-surface contract drifted' (post-mortems was the unclassified
surface) and 'tracked .agents state' failures. The .gitignore policy already
includes /.agents/ rules — no .gitignore change needed.
Pass-1 next-work entry corrected: source field was 'post-mortem', valid enum
is 'post-mortem-finding' per docs/contracts/next-work.schema.md.
Schema already accepts practices (pass-1 commit 235e5c20
2026-05-10 19:58:50 -04:00
a7a51f2c16
feat(standards): codify skill tier caps and codex registration
2026-05-03 23:00:11 -04:00
557e4af9ec
feat(codex): cap skills-codex description catalog and add --repair-shape audit
...
Adds a 2400-char aggregate budget for skills-codex/*/SKILL.md `description:`
fields in tests/skills/test-token-budgets.sh, then trims each skill's description
to fit (catalog now 2146/2400). Both Claude and Codex SKILL.md descriptions
are kept in sync; codex .agentops-generated.json hashes regenerated.
Adds --repair-shape to scripts/audit-codex-hooks.sh: when ~/.codex/hooks.json
is missing or in legacy-flat shape, rewrites it from hooks/codex-hooks.json
with the active plugin_root (read from .agentops-codex-install.json) and
backs up any prior file. Covered by new test_repairs_legacy_flat_shape.
Memory decay (4 .agents/ files) bumped by the SessionStart inject hook.
2026-04-30 15:16:59 -04:00
0496441989
Reduce skill catalog context footprint
2026-04-24 00:52:27 -04:00
98e581989c
codex: retire stale artifact provenance metadata
2026-04-01 13:10:42 -04:00
3f6bb2bda4
chore(codex): sync Codex skills for 6 new lifecycle skills
...
Add Codex variants (SKILL.md, prompt.md, markers) for test, review,
refactor, deps, perf, and scaffold. Wire cross-references in 8 existing
Codex skill copies. Update catalog and manifest.
2026-03-27 19:39:12 -04:00
b5316baef7
fix: align codex skill bundle with runtime contract
2026-03-21 10:08:27 -04:00
8e59cf1389
fix(skills-codex): audit + fix 60+ findings, strengthen CI gates
...
Skills content fixes:
- Add metadata.tier to all 54 skills-codex/ frontmatter
- Fix wrong-directory cross-refs in 11 skills (skills/ → ../)
- Remove Claude primitive leakage from 13 skills (TaskCreate,
AskUserQuestion, read_file, Agent tool, claude-code-latest-features)
- Fix dead refs, link missing references, remove orphaned Claude files
- Fix malformed ..$X link syntax in brainstorm, codex-team, rpi, validation
- Minor skills/ fixes: release refs, using-agentops count, push sections
CI gate hardening (false-pass elimination):
- heal.sh: scan skills-codex/, add MISSING_TIER/MALFORMED_LINK/DUPLICATE_REF
- audit-codex-parity.py: +7 Claude primitive patterns, +WRONG_XREF_DIR
- validate-links.sh: add skills-codex/ to scan scope (726 → 1117 links)
- validate-codex-generated-artifacts.sh: frontmatter check, invoke audit
2026-03-15 13:51:49 -04:00
2abe004643
feat: complete codex-first skill rollout
2026-03-08 12:49:35 -04:00
9205270833
Harden local codex skill validation
2026-03-07 13:26:49 -05:00
e0e21e3535
feat: add native Codex plugin install support
2026-03-07 07:30:08 -05:00
7d65010131
chore: regenerate codex-native skills (modular layout, 49 skills)
...
Generated by sync-codex-native-skills.sh with modular layout.
References and scripts copied as files instead of inlined.
Overrides applied for 9 skills. Parity validated: 49/49.
2026-02-26 11:02:17 -05:00
ab8df91ced
feat(codex): add Codex-native skill format and install/sync scripts
...
- skills-codex/: 53 skills converted to Codex-native agents.md format
- install-codex-native-skills.sh: install to ~/.codex/agents/
- sync-codex-native-skills.sh: sync from source skills/ to skills-codex/
- test-codex-native-install.sh: integration tests for the install pipeline
2026-02-25 08:44:19 -05:00
Bo