Commit Graph

7 Commits

Author SHA1 Message Date
Bo 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
Bo bdd62816ea docs(skills): add trigger markers to judgment-tier skills (ag-okfu #judgment-wave) (#767)
## What

Wave 1 of **ag-okfu** — adds an explicit `Use when:` discovery trigger
clause to the 8 **judgment-tier** skills: `council`, `design`,
`post-mortem`, `pre-mortem`, `red-team`, `review`, `validate`, `vibe`.

`scan_descriptions.py` flagged 73/81 skills with no trigger marker — a
silent skill-selection risk since runtime discovery is pure LLM
reasoning over the `description` field. The judgment tier ships first
because mis-selection there (e.g. grabbing `review` when you needed
`validate`) is the most costly.

## Why this slice

The bead says *"wave by metadata.tier."* This is one coherent wave = one
PR with a single rollback semantic. Remaining tiers (execution 22,
knowledge 8, meta 8, session 6, background 5, product 5, contribute 4,
cross-vendor 3, library 3, orchestration 1) ship as follow-on waves.

## Evidence

- Corpus missing-trigger count: **73 → 65** (the 8 judgment skills now
pass).
- `python3 skills/skill-builder/scripts/scan_descriptions.py skills
--strict` — all 8 judgment skills report `has_trigger=True`.
- `bash scripts/generate-registry.sh --check` → `OK: registry.json is up
to date` (regenerated, descriptions embedded).
- `markdownlint` clean on all 8 changed SKILL.md files.

## Notes

- Does **not** close ag-okfu — the `--strict` gate stays red until all
tiers are done. Advances the bead; unblocks nothing yet (ag-cx7d ratchet
waits on full corpus clean).

Bounded-context: BC1-Corpus
Evidence: skill-domain-map golden gate
2026-06-06 11:33:18 -04:00
Bo 6844eac751 feat(validate): executable acceptance for the unified validator (soc-sg44k #validate-hexagon) (#441)
soc-qk4b skill-hexagon-crank — high-traffic peripheral skill. /validate
(driving-adapter, consumes validation) lacked a .feature + had no
References section.

- skills/validate/references/validate.feature (NEW): any artifact →
verdict.v1 PASS/WARN/FAIL; --mode selects shape; 8-mode budget
- added Reference Documents section linking it; registry regenerated

consumes [validation] already filled — acceptance-only.

How tested: lint-skills ✓ validate (238 lines); scenarios --lint 0
errors; codex parity passed; registry up to date.
Sibling: acceptance-only crank like /pre-mortem #440.

NOTE: claude-review infra-red (weekly limit, resets May 25) —
operator-authorized bypass when sole red.

Closes-scenario: soc-sg44k#validate-hexagon
Bounded-context: BC4-Validation
Evidence: skills/validate/references/validate.feature
2026-05-23 02:33:11 -04:00
Bo d69f9f0c13 feat(architecture): intent-to-loop hexagon doc + BDD skill scaffolding (soc-4d0r) (#321)
## What

Foundation slice for the **soc-qk4b** epic ('TDD-crank all skills into
intent-to-loop hexagons'). The epic description listed these artifacts
as 'What already exists' — but they were never committed to main.
Without them, the 6 sub-issues (`soc-qk4b.1` through `.6`) cannot start.

## New

`docs/architecture/intent-to-loop-hexagon.md` — process-level hexagon
connecting [Ports and
Adapters](../blob/main/docs/architecture/ports-and-adapters.md)
(structure) to [Operating
Loop](../blob/main/docs/architecture/operating-loop.md) (execution).
Defines the 8-port chain with driving/driven/guard adapters and
done-state rules:

```
Intent
  -> shape_intent      -> AcceptanceExample
  -> persist_intent    -> WorkItem / Bead
  -> plan_slices       -> Slice
  -> execute_slice     -> implementation
  -> execute_wave      -> wave packet
  -> validate_acceptance -> CriterionVerdict
  -> record_evidence   -> Evidence
  -> steer_goal        -> LearningDisposition
```

## Skill changes

Source-of-truth in `skills/`, mirrored to `skills-codex/` (re-hashed via
`scripts/regen-codex-hashes.sh`):

| Skill | Change |
|---|---|
| `plan` | Require Gherkin block or upstream-scenario link for
feature/bug/product-facing behavior issues; `hexagon:` boundary block
for non-trivial plans and beads. |
| `discovery`, `rpi`, `validate`, `validation`, `beads`,
`shared/validation-contract` | Reference the intent-to-loop hexagon as
the boundary contract. |

## Doc plumbing

- `docs/architecture/{index,operating-loop,ports-and-adapters}.md` +
`docs/contracts/skill-ports-and-adapters.md`: cross-link to new hexagon.
- `docs/templates/{intent-issue,slice-validation}.md`: carry hexagon
block into intent issues and slice validation plans.
- `mkdocs.yml`, `docs/documentation-index.md`: register new doc in nav.

## AGENTS.md

- bd integration block regenerated (`v:1 profile:full hash:f65d5d33`).
- Session Completion section added with **conditional** `bd dolt push`
wording — passes `scripts/validate-bd-closeout-contract.sh`.

## Validation

- ✅ `scripts/pre-push-gate.sh --fast`: passed (1 pre-existing warn on
`scenarios/trace` executable-spec link integrity, unrelated)
- ✅ `scripts/validate-bd-closeout-contract.sh`: passes
- ✅ `scripts/regen-codex-hashes.sh`: 7 manifest hashes updated for
parity
- ✅ All 8 codex JSON files: syntactically valid
- ✅ Self-review per pre-commit hook: no removed error handling, no
changed defaults, no silent data loss

## Origin

Discovered during analysis of merged branch
`refactor/council-mode-taxonomy-soc-ml4l` (PR #293) on 2026-05-18 — the
BDD/hexagon scaffolding sat uncommitted in the worktree after #293
merged. Filed as `soc-4d0r` with `discovered-from: soc-qk4b`. This PR
lands the work cleanly off fresh `main`.

## Unblocks

- soc-qk4b (epic)
- soc-qk4b.1 — Control ledger for 77-skill hexagon crank
- soc-qk4b.2 — Loop priority skills (hexagon/TDD crank)
- soc-qk4b.3 — Factory priority skills
- soc-qk4b.4 — Corpus priority skills
- soc-qk4b.5 — Validation priority skills
- soc-qk4b.6 — Runtime priority skills

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-authored-by: Codex <codex@example.invalid>
2026-05-18 16:48:14 -04:00
Boden Fuller 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
Boden Fuller c3da963043 feat(practice): pass-12 wave 4 — cli/ tail (173 files) + skills/curate, skills/validate
Final wave to close out the practice citation backfill epic. Adds // practices:
declarations to the remaining 173 cli/cmd/ao/*.go files across 77 prefix
families (agentopsd, app, autodev, beads, codex, compile, completion, config,
constraint, contradict, corpus, curate, doctor, dream, eval, evolve, gate,
golden, handoff, harvest, hooks, init, integration, json, kill, llmwiki,
lookup, main, memory, mine, parity, plans, property, quickstart, registry,
regression, schedule, scope, search, seed, skill, status, store, task, temper,
template, testutil, trace, tracker, uat, version, vibe, watch, workflow,
worktree, ...).

Also covers two skills that landed via the rebased product launch commit:
- skills/curate → [wiki-knowledge-surface, lean-startup]
- skills/validate → [design-by-contract, llm-eval-harness]

**Final state: 756/756 with practices, 0 missing, 0 invalid.**
Every primitive in skills/, hooks/, schemas/, evals/, and cli/ now declares
which practices it embodies, satisfying the PRACTICE.md registry contract.

Codex parity hashes regen'd for curate + validate. Pass 1+2 of pre-push --fast
PASSED; baseline-audit downgraded from FAIL to WARN (advisory only) once
cli/bin/ao was rebuilt with Suite.Practices field.
2026-05-11 07:50:28 -04:00
Boden Fuller 3e374d842d feat(product): codify AgentOps 3 launch path 2026-05-10 23:22:14 -04:00