The worker guard's bulk-staging block lowercased the command before matching
`*git add -a*`, which could match `-a` + `-u` clusters or (more subtly) any
text starting with `-a` after `git add `. Legitimate selective patterns like
`git add -u` (update-only) happened to slip past only because `-u` doesn't
contain `-a`, but the intent was already murky.
Split the patterns:
- commit/push/--all/. match against the lowercased command (subcommand
names can reasonably be case-insensitive in alias contexts)
- `-A` is checked against the raw command, so only the uppercase bulk flag
trips the block
Adds four regression tests: `-A` still blocks, `--all` still blocks,
selective `-u` is allowed, filenames containing `-a` are allowed.
Embedded hook copy resynced via `make sync-hooks`.
https://claude.ai/code/session_01TZeRkm97SrPchDwPsD41rd
Unblocks CI on this PR. Both were pre-existing drift on main:
- cli/embedded/.../test-pyramid.md: re-ran `cd cli && make sync-hooks`
to match source under skills/standards/references/. Fixes the
embedded-sync and go-build `Verify embedded hooks in sync` gates.
- skills-codex/{crank,quickstart,standards}/.agentops-generated.json
and skills-codex/.agentops-manifest.json: re-ran
`scripts/regen-codex-hashes.sh`. Fixes the codex-runtime-sections
`Validate Codex generated artifacts` gate.
https://claude.ai/code/session_01W5b6kSdX9wEDgXfVGCXTZa
## Docs site — boshu2.github.io/agentops
- Replace Jekyll minima with MkDocs Material (slate dark palette default)
- Landing hero scoped to .landing-hero (no gradient bleed on inner pages)
- Section landings (getting-started, architecture, reference, contracts, levels) with narrative ledes
- Generate skill catalog + per-skill pages from skills/*/SKILL.md at build
- Generate CLI reference from cli/docs/ at build (fails build on missing source)
- Fix every internal link via one-shot migration (scripts/migrations/2026-04-19-fix-docs-links.py)
- Wire mkdocs build --strict into pre-push gate (Check 25a)
- Replace .github/workflows/pages.yml with .github/workflows/docs.yml (actions/deploy-pages)
- README + docs/CONTRIBUTING updated with docs-build toolchain on-ramp
- tests/docs/validate-links.sh patched to understand mkdocs-generated paths
## RPI orchestrator strict-delegation contract
- Strict sub-skill delegation is now the default for /rpi, /discovery, /validation. No --full flag — always on.
- Canonical contract in skills/shared/references/strict-delegation-contract.md (plus Codex mirror)
- Forged learning with detection phrases + corrective actions (ao-inject-ready)
- Rename --no-lifecycle -> --no-scaffold in /discovery (Claude + Codex) with deprecation alias through v2.40.0
- Harden inline-work hotspots with orchestrator-owned markers in /crank STEPS 3a.3, 6.5, 8.7 + Inline Work Policy footer
- Flag consistency: --auto and --interactive scopes documented; --complexity syntax formalized
- CHANGELOG [Unreleased] documents + scaffolds; runtime hook enforcement explicitly deferred
## fix(hooks): go-test-precommit skips when no Go files staged
- Previously ran go vet + go build unconditionally, blocking non-Go commits when Go toolchain was missing or at a different version
- Now checks staged diff and exits cleanly if no *.go or go.{mod,sum,work} files are staged
- Applied to both hooks/ (source) and cli/embedded/hooks/ (synced)
Provenance: full RPI lifecycle with strict delegation at every phase boundary (Phase 1 Skill(discovery) -> Phase 2 Skill(crank) -> Phase 3 Skill(validation) -> Skill(vibe), Skill(post-mortem), Skill(retro)).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Previously the pre-mortem gate fell back to UNLOCKED on missing,
unparseable, stale, or unrecognized state. A broken state file
silently disabled the safety gate. Flips default fallback to strict:
lock on any ambiguity, unlock only on explicit unambiguous evidence.
Strict default rules:
- Missing state file: BLOCKED
- Unparseable state (jq -e . fails): BLOCKED with clear error
- Verdict not in allow-list (passed|locked|ok|ratchet|approved): BLOCKED
- Missing epic-id or missing bd CLI in strict mode: BLOCKED
- Valid recognized verdict: ALLOWED
- Run-scoped orchestration log / epic-scoped council artifact / ratchet
status locked|skipped / chain.jsonl pre-mortem done: ALLOWED
Bypass: AGENTOPS_PREMORTEM_GATE_BOOTSTRAP=1 unlocks with mandatory
stderr warning 'WARN: pre-mortem-gate bypassed via ...'. Distinct
from the silent AGENTOPS_HOOKS_DISABLED=1 kill switch.
Legacy AGENTOPS_PREMORTEM_FALLBACK=open restores the previous silent-
allow behavior for operators who need the old semantics during the
transition.
Adds 8 new behavioral tests (20 total pass): missing/unparseable/
passed/expired/unknown-verdict/bootstrap/kill-switch/legacy-open.
Synced to cli/embedded/hooks/pre-mortem-gate.sh.
Consumes ag-yhr 'Harden pre-mortem gate fallback to locked-state
semantics'.
lib/hook-helpers.sh exports BEADS_DOLT_SERVER_PORT with override via
${BEADS_DOLT_SERVER_PORT:-3307} so users can still override per shell.
All hooks that source hook-helpers.sh automatically inherit the port.
scripts/bd-audit.sh and scripts/bd-cluster.sh are standalone bd callers
that do not source hook-helpers.sh, so they get the same export inline.
cli/embedded/lib/hook-helpers.sh synced via make sync-hooks.
Consumes ag-co7 'Export BEADS_DOLT_SERVER_PORT=3307 in shell env'.
Two related compile.sh bugs fixed together (both in the batching script).
1. Incremental + --max-batches corrupted hash state. compile_single_batch
persisted hashes for every file in the inventoried batch regardless of
whether an article was actually written; when the outer loop hit
MAX_BATCHES, uncompiled files got their hashes saved and were skipped
forever on the next --incremental run. Now save_hashes runs only when
the batch produced output, and only for files with an emitted article.
2. claude-cli wraps its output in ```markdown ... ``` fences. Every article
from real smoke runs inherited the cruft. Fixed in two places:
- system prompt now explicitly forbids markdown fences
- article splitter skips lines matching the fence regex as defense in depth
Adds skills/compile/scripts/tests/test-fence-stripping.sh fixture.
Syncs cli/embedded/ copy via make sync-hooks.
The prior implementation used recursive self-invocation with env-var
prefix assignment (BATCH_SIZE=$total MAX_BATCHES=0 compile_articles < "$tmp")
to disable further batching inside each sub-call. That worked but was
opaque and hard to test.
Split into two clear functions:
- compile_articles() — chunks changed_files into BATCH_SIZE slices and
iterates compile_single_batch per slice via an explicit for-loop.
No recursion, no env prefix trick.
- compile_single_batch() — compiles one chunk via a single LLM call;
caller is responsible for chunking.
The integration test (TestRunCompile_EndToEnd_FixtureCorpus) exercises
multi-batch behavior end-to-end and still passes. No flag surface
changes. Embedded copy re-synced.
Closes na-pmx1.6.
Fixes three onboarding defects that surfaced on 2026-04-15 when running
against a global ~/.agents corpus from a non-git home directory:
1. `ao compile --full` failed in the installed bundle with
"open skills/compile/scripts/compile.sh: file does not exist". The
Makefile's sync-hooks target never copied compile.sh into
cli/embedded/skills/, so the //go:embed all:skills fallback had
nothing to fall back to. Fix: sync-hooks now seeds the script and a
regression test (TestMaterializeCompileScriptFallsBackToEmbedded)
asserts the embedded copy resolves when no local skills/ exists.
2. Headless compile implicitly required OLLAMA_HOST / OPENAI_API_KEY /
ANTHROPIC_API_KEY with no actionable error when none were set, and
ignored a locally installed `claude` CLI. Fix: resolveCompileRuntime
auto-detects the `claude` binary and selects claude-cli runtime (no
API key needed — inherits Claude Code auth). preflightCompileRuntime
fails fast with an actionable error naming the exact env var to set.
compile.sh gains a matching claude-cli backend and a --preflight flag.
3. The headless compiler concatenated all changed files into one LLM
prompt, which is unworkable on 2000+ file corpora. Fix: compile.sh
batches by --batch-size (default 25) and --max-batches (default
unlimited); ao compile propagates both flags.
Onboarding gaps:
- $quickstart now detects a global ~/.agents corpus (GLOBAL_AGENTS=true)
and, when GIT=false + AO=true, surfaces a harvest → compile →
knowledge-activation path instead of only suggesting `git init`.
- Harvest SKILL.md clarifies that promotion writes to ~/.agents/learnings/
(not ~/.agents) and adds a "which skill do I need?" decision table.
- Compile SKILL.md documents the claude-cli runtime and batching flags.
- skills-codex/compile/scripts/compile.sh wrapper now falls back through
multiple candidate paths and finally delegates to `ao compile`, so an
installed bundle without a sibling skills/ checkout still works.
Tests added:
- TestMaterializeCompileScriptFallsBackToEmbedded
- TestResolveCompileRuntime
- TestPreflightCompileRuntimeErrors (5 subtests)
- TestPreflightCompileRuntimeSuccess
- TestCompileScriptOptionsPassesBatchFlags
- TestQuickstartSkillCoversGlobalCorpus (both parity surfaces)
Verification:
cd cli && go vet ./... && go test ./... # all green
bash skills/heal-skill/scripts/heal.sh --strict # clean
bash tests/docs/validate-doc-release.sh # PASS
bash scripts/check-contract-compatibility.sh # 0 failures
bash scripts/regen-codex-hashes.sh # 3 skills rehashed
bash scripts/generate-cli-reference.sh # COMMANDS.md regenerated
1. Add CHANGELOG sync check (check 36) to pre-push-gate.sh — fails if
root CHANGELOG.md differs from docs/CHANGELOG.md
2. Add 250-line limit guard to edit-knowledge-surface.sh for SKILL.md
files — warns at 240, errors at 250
3. Add TestMain to cli/cmd/ao/ that clears AGENTOPS_RPI_RUNTIME* env
vars so per-test t.Setenv is unnecessary
4. Broaden CLI docs parity check (24b) to trigger on any cmd/ao/*.go
change, not just go build changes
5. Wire --fast flag into .githooks/pre-push for faster push-time gates
Bonus: fix pre-existing pipefail bug in flywheel health check (35) that
silently killed all subsequent checks.
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.
Hook polish: add missing kill switch to go-test-precommit.sh, fix shebang
and bracket style in hook-helpers.sh, shellcheck annotations for
finding-compiler.sh and session-start.sh.
Test infra: refactor defrag.go writeDefragReport to accept io.Writer,
consolidate chdirTempWorkspace into chdirTo delegation, add godoc to
testutil_test.go helpers.
Skills: normalize output_contract quoting in brainstorm, design,
red-team, review SKILL.md frontmatter.
Traditional test pyramid optimized for human writing cost (L1 cheapest).
AI agents eliminate that cost differential. New shape optimizes for
bug-finding value: L2 integration first (3x weight, where bugs live),
L1 unit always (regression safety). Evidence: 946 council verdicts
showed L0-L1 found zero production bugs, L2+ found all.
Updated: test-pyramid.md, vibe weighting, CLAUDE.md.
Epic D: Add pre-spawn worker detection to git-worker-guard (blocks worktree-add
and agent-spawn from workers). Enhance check-file-manifest-overlap.sh edge cases.
Wire validate-swarm-evidence.sh into CI. Fix .agents/retros→retro in index.go
and init.go. Add grep-for-existing-functions to swarm worker template.
Epic E: Replace partial embedded check in pre-push-gate with full
validate-embedded-sync. Lazy-init git rev-parse in research-loop-detector.
Add retag idempotency guard (skip if tag already at HEAD). Add git_sha to
release-artifacts.json manifest. Empty stdin guard in go-test-precommit.
Inspired by patterns discovered in Claude Code's npm source map leak:
- Add hook failure budget to lib/hook-helpers.sh (MAX_CONSECUTIVE_HOOK_FAILURES=3,
configurable via AGENTOPS_HOOK_FAILURE_CAP) — prevents runaway hook loops
- Add metadata.stability field (experimental|stable) to skill frontmatter schema
with heal.sh validation (H010) and skill-conventions documentation
- Add quality-signals.sh hook detecting repeated prompts and correction patterns,
logging to .agents/signals/session-quality.jsonl with defined schema
- Document orchestration-as-prompt as a first-class pattern in shared references,
linked from crank, swarm, evolve, rpi skills with codex parity
Add doc-release, contract-compatibility, hook-preflight, hooks-doc-parity,
ci-policy-parity, shellcheck, symlink-rejection, learning-coherence, and
orphan-hooks checks to pre-push-gate.sh (checks 25-33). Add fast-mode
detection for docs/shell/learning file categories so new checks only run
when relevant files change.
Also fix shellcheck warnings in task-validation-gate.sh (SC2053 glob
directives) and remove unused error_msg in watch-codex-stream.sh.
- harvest.go: use empty defaults with ~/ descriptions instead of baking $HOME
into flag defaults, resolving cli-docs-parity failures across environments
- athena-session-defrag.sh: swap stat order to try Linux stat -c first, fixing
integer expression error when macOS stat -f succeeds but returns mount path
- skills-codex/validation: replace ao codex stop with ao codex ensure-stop to
pass codex lifecycle guard validation
The session-start hook previously wrote a minimal 3-line gitignore
that only allowed .gitignore and README.md. This meant fresh repos
would lack the subdirectory-level deny rules, allowing session
artifacts to leak into git tracking on the first `git add`.
Now writes the same comprehensive gitignore as .agents/.gitignore
in the repo root: subdirectories allowed but contents denied, with
explicit exceptions for signposts, releases, plugins, and evolve state.
Claude