Rename the athena skill to compile — a descriptive name that communicates
what it actually does. Extend with Karpathy's LLM Knowledge Bases architecture:
- New compile phase: LLM reads raw .agents/ artifacts and produces interlinked
markdown wiki at .agents/compiled/ with index.md, log.md, backlinks
- New lint phase: detects contradictions, orphan pages, stale claims, coverage gaps
- Pluggable compute backend via AGENTOPS_COMPILE_RUNTIME (ollama|claude|openai)
- Hash-based incremental compilation (only recompile changed sources)
- compile.sh engine with security fixes (no shell injection, path traversal guard)
- Full rename across 93 files: skills, docs, CLI, tests, hooks, scripts, codex
Existing Mine → Grow → Defrag cycle preserved as phases within the larger
compile workflow. No vector DB — compiled wiki IS the retrieval layer.
gc executor is now the default when gc binary (>= 0.13.0) and
city.toml are available. Falls back to stream executor otherwise.
Schema fixes found by L3 live controller tests:
- GCController uses running (bool), not state (string)
- gc event emit uses --payload flag, not --data
Test infrastructure: gcMock with TestHelperProcess pattern for
deterministic exec injection. 107 test cases across L1 (unit),
L2 (component chain), and L3 (live gc controller).
Skills updated to document gc as default runtime mode.
Crank failure taxonomy updated from tmux to gc session commands.
- Regenerate skills-codex with discovery and validation directories
- Add discovery/validation to codex-overrides catalog
- Trim discovery SKILL.md (276→215) and rpi SKILL.md (261→243) under
250-line limit by extracting content to references/
- Add complexity-scaled council gates to rpi SKILL.md (fixes T14-T16, T32)
- Add required section headings to rpi SKILL.md (fixes validate.sh)
- Regenerate CLI docs for --auto-extract description change
The CLI namespace was flattened in 4fd2512c (remove know.go, work.go,
quality.go), but skills-codex/ was never updated. Replace all stale
two-token prefixes with their flat equivalents across 17 SKILL.md files:
ao know forge → ao forge
ao know inject → ao inject
ao know search → ao search
ao know lookup → ao lookup
ao know temper → ao temper
ao quality flywheel → ao flywheel
ao quality pool → ao pool
ao quality metrics → ao metrics
ao quality maturity → ao maturity
ao quality badge → ao badge
ao quality constraint → ao constraint
ao quality contradict → ao contradict
ao quality dedup → ao dedup
ao quality curate → ao curate
71 occurrences fixed. Codex agents following these skills will no longer
invoke commands that return "unknown command".
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.
Council vibe found 9 stale references after the threshold changes:
- Auto-prune comment: "opt-in" → "opt-out" (default is now 1)
- Add AGENTOPS_AUTO_PRUNE to docs/ENV-VARS.md
- 5+ docs said "manual (default)" for startup mode → now "lean"
- Add stub rejection test for pool_ingest "no significant learnings"
- Update 8 stale test comments (0.7→0.55, harmful>=5→>=3, conf<0.2→<0.3)
- Fix helpers2_test boundary confidence 0.19→0.29 for new 0.3 threshold
- Fix json_validity_test fixture data to match new thresholds
- 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
Boden Fuller