mirror of https://github.com/boshu2/agentops.git synced 2026-09-14 15:08:13 +08:00

Files

T

boshu 4a7c6a0701 feat(gates): docs.skill-refs --all-docs — widen the 6-file skill-ref gate to live docs + SKILL-ROUTER sync (age-gate-the-ungated-egwt.5)

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.

2026-07-01 18:12:53 -04:00

2.2 KiB

Raw Blame History

description

description
Execute all unblocked issues in parallel using sub-agents

/implement-wave

Runs all ready issues in parallel. Each issue gets a sub-agent. Results batched into single commit.

Usage

/implement-wave

What's Different from L3

At L4, parallelization speeds execution:

Multiple issues run simultaneously
Sub-agents handle each issue independently
Single commit captures all wave changes
Dramatically faster for independent work

How It Works

Claude runs BEADS_DIR="$(ao beads dir)" br ready to find unblocked issues
Spawns sub-agent for each issue (max 3 per wave)
Sub-agents work in parallel via Task tool
Results merged and validated
Single commit closes all wave issues

Why max 3? Each subagent returns results that accumulate in context. Capping at 3 prevents context overflow on complex issues while still providing meaningful parallelism.

Output

Wave 1: 3 issues ready

Launching sub-agents:
  → agentops-abc: Add login form
  → agentops-def: Add logout button
  → agentops-ghi: Add session display

[Sub-agents complete...]

All 3 issues completed successfully.

$ git commit -m "feat: add auth UI components

- Login form (agentops-abc)
- Logout button (agentops-def)
- Session display (agentops-ghi)

Closes: agentops-abc, agentops-def, agentops-ghi"

$ BEADS_DIR="$(ao beads dir)" br close agentops-abc agentops-def agentops-ghi

Wave 1 complete. Run `br ready` for Wave 2.

Example

You: /implement-wave

Claude: Checking ready issues...

$ BEADS_DIR="$(ao beads dir)" br ready
1. [P1] agentops-xyz: Create user model
2. [P1] agentops-abc: Create order model
3. [P2] agentops-def: Add database migrations

Launching 3 sub-agents...

[3 parallel agents work...]

✓ All complete. Tests passing.

$ git commit -m "feat: add data models and migrations"
$ BEADS_DIR="$(ao beads dir)" br close agentops-xyz agentops-abc agentops-def

Done. Next wave has 2 issues ready.

When to Use

Multiple independent issues ready
Issues don't share file dependencies
Want maximum velocity

BEADS_DIR="$(ao beads dir)" br ready - See next wave
/crank - Run next wave
/post-mortem - Extract learnings after completing plan

2.2 KiB Raw Blame History