mirror of
https://github.com/boshu2/agentops.git
synced 2026-09-14 15:08:13 +08:00
4a7c6a0701
Add an --all-docs mode to check-doc-skill-refs.sh that scans the union of the pinned doctrine files PLUS the full LIVE docs/** set (scripts/lib/docs-scope.sh), ratcheted by a new filename-pinned shrink baseline (scripts/.docs-skill-refs-baseline). Two-way ratchet: a non-baselined live doc with a dead `/skill` ref FAILS; a baselined file that no longer offends FAILS demanding a prune. Detection stays slash-syntax + headings only (never bare skill names). Default (no-flag) behavior is byte-identical. docs/SKILL-ROUTER.md (the curated router) is covered by --all-docs (a live docs/** file, never baselined) so a dead ref there FAILS strict, without perturbing the byte-identical default doc count. seed.go docs.skill-refs row: Match widened to docs/** + the baseline + the lib; Args set to [--all-docs --strict]. Burn-down (long-tail only): repointed retired `/retro`->/post-mortem, `/vibe`->/validate, `/ratchet`->/flywheel, `/research-multi`->/research, `/implement-wave`->/crank, and reworded the retired `/dream` across 13 docs/levels + docs/workflows + docs/philosophy pages, then pruned them from the baseline (91 -> 78 offenders). Owner-locked pages (comparisons/getting-started/positioning) stay baselined. Bats twin tests/scripts/check-doc-skill-refs-all-docs.bats covers all the modes.
1.6 KiB
1.6 KiB
L5 — Orchestration
Full autonomous operation with /crank.
What You'll Learn
- Using
/crankfor epic-to-completion - The ODMCR reconciliation loop
- Swarm vs Crew execution modes
- Integration with the NTM + MCP Agent Mail substrate for parallel workers
Prerequisites
- Completed L4-parallelization
- Comfortable with wave execution
- Understanding of beads issue tracking
Available Commands
| Command | Purpose |
|---|---|
/crank |
Autonomous epic-to-completion |
/crank |
Same as L4 |
/plan <goal> |
Same as L3 |
/research <topic> |
Same as L2 |
/implement [id] |
Same as L3 |
/post-mortem [topic] |
Same as L2 |
Key Concepts
- Crank: Autonomous epic execution - runs until ALL children are CLOSED
- ODMCR loop: Observe → Dispatch → Monitor → Collect → Retry
- Swarm mode: Dispatches to parallel worker panes via the NTM tmux swarm, coordinated through MCP Agent Mail
- Crew mode: Executes sequentially via
/implement
Crank Flow
/crank <epic>
↓
Observe (BEADS_DIR="$(ao beads dir)" br show, br ready)
↓
Dispatch (NTM swarm pane or /implement)
↓
Monitor (convoy status)
↓
Collect (close completed)
↓
Retry (handle failures)
↓
Loop until epic CLOSED
Execution Modes
| Mode | When | How |
|---|---|---|
| Crew | Default, single-agent | Sequential /implement calls |
| Swarm | Multi-agent contention/durability | Parallel dispatch via NTM tmux swarm + MCP Agent Mail |
Mastery
At L5, you can hand off entire epics to /crank and trust autonomous completion.