mirror of
https://github.com/boshu2/agentops.git
synced 2026-09-14 15:08:13 +08:00
Bo
c6558508d1
AgentOps' 55-skill catalog contained overlapping entry points, stale
routes and descriptions that could lose meaningful guidance in the Codex
projection. This change consolidates 21 roots into existing owners,
leaving 34 distinct skills and a generated, task-oriented menu. README
documents every retired name and its replacement.
Planning now establishes observable behavior in the caller's existing
intent, using proportional Given/When/Then examples and domain language.
Implementation and final validation carry those same examples forward.
Original adaptations informed by Matt Pocock's engineering skills
strengthen existing owners rather than adding a new workflow. Routine
edits need no mandatory plan, coverage report, mutation exercise or
learning artifact.
Codex retains complete source descriptions and translates explicit-only
invocation policy. All descriptions fit the existing 180-character
limit; the root instructions retain their 250-line limit. Generated
catalogs, projections, routers, moved references/helpers and their live
consumers are updated together. RPI remains explicitly selected.
Validation passed: projection/conformance checks, the local aggregate
(10 passed; one existing optional-directory skip), and exact-commit CI
covering the complete gate registry, Bats, Go build/vet/race/coverage,
Windows and security. A fresh author-distinct reviewer passed all
acceptance criteria over the complete 573-path subject at
aa642a55d6, including the installed-link
and protected-backup changes. Review findings were repaired and
revalidated. Existing ranker goldens are regression checks, not
model-quality measurements. A fixed six-case fresh-context pilot
supplied an exact candidate menu: three of four targeted cases loaded
expected guidance, a simple refactor selected no skill, and both
no-skill controls selected none. No wrong owner was selected. This pilot
preceded final wording repairs for existing ranker/context limits; it
does not establish installed automatic activation, coding benefit or
savings. No live coding task was run in that pilot.
142 lines
8.3 KiB
Plaintext
142 lines
8.3 KiB
Plaintext
# Codex parity twins (self-contained) carry source cross-skill deep-links into
|
|
# swarm's refs, but swarm's BESPOKE twin deliberately omits the Claude-coupled
|
|
# target (shared-checkout-discipline.md -> worktree-isolation.md describes
|
|
# `claude agents`/Claude teams). The link resolves in the canonical skills/ tree;
|
|
# the Codex twin tree intentionally drops the Claude-specific target. Known,
|
|
# accepted cross-skill limitation — not a real broken doc.
|
|
skills-codex/using-atm/SKILL.md:../swarm/references/shared-checkout-discipline.md
|
|
skills-codex/dual-pane-atm/SKILL.md:../swarm/references/shared-checkout-discipline.md
|
|
|
|
# Meta-observer links (removed targets, kept for reference)
|
|
docs/workflows/meta-observer/README.md:../commands/launch-meta-observer.md
|
|
docs/workflows/meta-observer/README.md:../commands/start-worker.md
|
|
docs/workflows/meta-observer/README.md:../commands/worker-brief.md
|
|
docs/workflows/meta-observer/README.md:../agents/meta-observer.md
|
|
docs/workflows/meta-observer/README.md:../agents/autonomous-worker.md
|
|
|
|
# Style guide example links (intentionally broken - illustrative examples)
|
|
docs/standards/markdown-style-guide.md:./references/detail1.md
|
|
docs/standards/markdown-style-guide.md:./references/detail2.md
|
|
docs/standards/markdown-style-guide.md:url
|
|
docs/standards/markdown-style-guide.md:./other-doc.md
|
|
docs/standards/markdown-style-guide.md:/Users/me/project/docs/guide.md
|
|
docs/standards/markdown-style-guide.md:./images/diagram.png
|
|
docs/standards/markdown-style-guide.md:image.png
|
|
|
|
# Vibe markdown-standards example links (copy of style guide examples)
|
|
|
|
# Standards reference example links
|
|
skills/domain/references/standards/markdown.md:url
|
|
skills/domain/references/standards/markdown.md:./docs/guide.md
|
|
|
|
# Doc skill template example links
|
|
skills/doc/references/generation-templates.md:../path/to/doc.md
|
|
skills-codex/doc/references/generation-templates.md:../path/to/doc.md
|
|
|
|
# Beads CLI reference (external doc references)
|
|
skills/beads/references/CLI_REFERENCE.md:DAEMON.md
|
|
skills/beads/references/CLI_REFERENCE.md:CONFIG.md
|
|
skills/beads/references/CLI_REFERENCE.md:../AGENTS.md
|
|
skills/beads/references/CLI_REFERENCE.md:GIT_INTEGRATION.md
|
|
skills/beads/references/CLI_REFERENCE.md:../LABELS.md
|
|
skills/beads/references/CLI_REFERENCE.md:../README.md
|
|
skills-codex/beads/references/CLI_REFERENCE.md:DAEMON.md
|
|
skills-codex/beads/references/CLI_REFERENCE.md:CONFIG.md
|
|
skills-codex/beads/references/CLI_REFERENCE.md:../AGENTS.md
|
|
skills-codex/beads/references/CLI_REFERENCE.md:GIT_INTEGRATION.md
|
|
skills-codex/beads/references/CLI_REFERENCE.md:../LABELS.md
|
|
skills-codex/beads/references/CLI_REFERENCE.md:../README.md
|
|
|
|
# Cross-directory references
|
|
docs/comparisons/README.md:../README.md
|
|
docs/brownian-ratchet.md:/.beads/issues/ol-rg3p
|
|
|
|
# Release notes template (CHANGELOG.md created at release time)
|
|
skills/release/references/release-notes.md:../../docs/CHANGELOG.md
|
|
skills-codex/release/references/release-notes.md:../../docs/CHANGELOG.md
|
|
|
|
# Go generics in backticks parsed as markdown links (false positive: `[T](err)`)
|
|
skills/domain/references/standards/go.md:err
|
|
skills-codex/domain/references/standards/go.md:err
|
|
cli/embedded/skills/domain/references/standards/go.md:err
|
|
|
|
# Auto-generated session files (concurrency text parsed as links)
|
|
cli/.agents/ao/sessions/2026-02-13-till-disable-it-with-cass-false-if-you-ever-want-7eb47b8.md:concurrency
|
|
cli/.agents/ao/sessions/2026-02-13-selected-version-result-suggested-version-based-7eb47b8.md:concurrency
|
|
skills/research/references/software-research.md:references/STRATEGIES.md
|
|
skills/research/references/software-research.md:references/OUTPUT-TEMPLATES.md
|
|
skills/research/references/software-research.md:references/EXAMPLES.md
|
|
skills/research/references/software-research.md:references/STRATEGIES.md
|
|
skills/review/references/MOCK_FINDER.md:references/DETECTION-METHODS.md
|
|
skills/review/references/MOCK_FINDER.md:references/DETECTION-METHODS.md
|
|
skills/review/references/MOCK_FINDER.md:references/DETECTION-METHODS.md
|
|
skills/review/references/MOCK_FINDER.md:references/DETECTION-METHODS.md
|
|
skills/review/references/MOCK_FINDER.md:references/AST-PATTERNS.md
|
|
skills/review/references/MOCK_FINDER.md:references/RESOLUTION-STRATEGIES.md
|
|
skills/review/references/DOMAIN_AUDIT.md:references/CHECKLISTS.md
|
|
skills/review/references/DOMAIN_AUDIT.md:references/TOOLS.md
|
|
skills/review/references/DOMAIN_AUDIT.md:references/CHECKLISTS.md
|
|
skills/review/references/DOMAIN_AUDIT.md:references/EXAMPLES.md
|
|
skills/review/references/DOMAIN_AUDIT.md:references/TOOLS.md
|
|
skills/review/references/BUG_SCANNER.md:references/TRIAGE.md
|
|
skills/review/references/BUG_SCANNER.md:references/TRIAGE.md
|
|
skills/review/references/BUG_SCANNER.md:references/FALSE-POSITIVES.md
|
|
skills/review/references/BUG_SCANNER.md:references/WORKFLOWS.md
|
|
skills/review/references/BUG_SCANNER.md:FALSE-POSITIVES.md
|
|
skills/review/references/DEEP_SCAN.md:references/TRIAGE.md
|
|
skills/review/references/DEEP_SCAN.md:references/PATTERNS.md
|
|
skills/review/references/DEEP_SCAN.md:references/TOOLS.md
|
|
skills-codex/doc/references/de-slopify.md:references/PATTERNS.md
|
|
skills-codex/doc/references/architecture-report.md:references/TEMPLATE.md
|
|
skills-codex/doc/references/architecture-report.md:references/TEMPLATE.md
|
|
skills-codex/doc/references/architecture-report.md:references/EXAMPLES.md
|
|
skills-codex/research/references/codebase-archaeology.md:references/LANGUAGES.md
|
|
skills-codex/research/references/codebase-archaeology.md:references/PATTERNS.md
|
|
skills-codex/research/references/codebase-archaeology.md:references/EXAMPLES.md
|
|
skills-codex/research/references/software-research.md:references/STRATEGIES.md
|
|
skills-codex/research/references/software-research.md:references/OUTPUT-TEMPLATES.md
|
|
skills-codex/research/references/software-research.md:references/EXAMPLES.md
|
|
skills-codex/research/references/software-research.md:references/STRATEGIES.md
|
|
skills-codex/review/references/MOCK_FINDER.md:references/DETECTION-METHODS.md
|
|
skills-codex/review/references/MOCK_FINDER.md:references/DETECTION-METHODS.md
|
|
skills-codex/review/references/MOCK_FINDER.md:references/DETECTION-METHODS.md
|
|
skills-codex/review/references/MOCK_FINDER.md:references/DETECTION-METHODS.md
|
|
skills-codex/review/references/MOCK_FINDER.md:references/AST-PATTERNS.md
|
|
skills-codex/review/references/MOCK_FINDER.md:references/RESOLUTION-STRATEGIES.md
|
|
skills-codex/review/references/DOMAIN_AUDIT.md:references/CHECKLISTS.md
|
|
skills-codex/review/references/DOMAIN_AUDIT.md:references/TOOLS.md
|
|
skills-codex/review/references/DOMAIN_AUDIT.md:references/CHECKLISTS.md
|
|
skills-codex/review/references/DOMAIN_AUDIT.md:references/EXAMPLES.md
|
|
skills-codex/review/references/DOMAIN_AUDIT.md:references/TOOLS.md
|
|
skills-codex/review/references/BUG_SCANNER.md:references/TRIAGE.md
|
|
skills-codex/review/references/BUG_SCANNER.md:references/TRIAGE.md
|
|
skills-codex/review/references/BUG_SCANNER.md:references/FALSE-POSITIVES.md
|
|
skills-codex/review/references/BUG_SCANNER.md:references/WORKFLOWS.md
|
|
skills-codex/review/references/BUG_SCANNER.md:FALSE-POSITIVES.md
|
|
skills-codex/review/references/DEEP_SCAN.md:references/TRIAGE.md
|
|
skills-codex/review/references/DEEP_SCAN.md:references/PATTERNS.md
|
|
skills-codex/review/references/DEEP_SCAN.md:references/TOOLS.md
|
|
|
|
|
|
# docs/CHANGELOG.md is kept byte-identical to the repo-root CHANGELOG.md
|
|
# (pre-push gate #36: diff -q CHANGELOG.md docs/CHANGELOG.md). Its links are
|
|
# root-relative so they resolve correctly in the canonical root copy; in the
|
|
# docs/ mirror they resolve one level too deep. The sync invariant forbids
|
|
# rewriting them in the mirror, so the mirror's root-relative targets are
|
|
# allowlisted here. Targets verified to exist at repo root.
|
|
docs/CHANGELOG.md:docs/3.1.md
|
|
docs/CHANGELOG.md:README.md
|
|
docs/CHANGELOG.md:docs/install-day2-ops.md
|
|
docs/CHANGELOG.md:docs/3.0.md
|
|
docs/CHANGELOG.md:docs/architecture/codebase-overview.md
|
|
|
|
# Corpus-flywheel skills demoted to the experimental tier ship NO Codex twin
|
|
# (age-focus-membrane-bookkeeper-m1wg.19): skills-codex/{forge,operationalize,...}
|
|
# were dropped. Kept parity twins that carry a source cross-skill deep-link to one
|
|
# of those dropped twins now dangle in the Codex tree only — the link still resolves
|
|
# in the canonical skills/ tree; the Codex twin tree intentionally omits the target.
|
|
# Known, accepted cross-skill limitation — not a real broken doc (same pattern as the
|
|
# swarm/using-atm bespoke-omission entries above).
|
|
skills-codex/skill-builder/SKILL.md:../forge/SKILL.md
|
|
skills-codex/implement/SKILL.md:../operationalize/SKILL.md
|