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

1.7 KiB

Raw Blame History

L3 — State Management

Add issue tracking with beads for structured work.

What You'll Learn

Using /plan to decompose work into issues
Beads commands for issue lifecycle
Tracking dependencies between tasks
Session close protocol

Prerequisites

Completed L2-persistence
Comfortable with .agents/ directory
br (beads_rust) CLI installed; invoke as BEADS_DIR="$(ao beads dir)" br

Available Commands

Command	Purpose
`/plan <goal>`	Decompose goal into beads issues
`/research <topic>`	Same as L2
`/implement [id]`	Execute specific issue, then close it
`/post-mortem [topic]`	Same as L2

Beads Commands

All commands take BEADS_DIR="$(ao beads dir)" so linked worktrees use the canonical private ledger:

BEADS_DIR="$(ao beads dir)" br ready --json             # Show unblocked issues
BEADS_DIR="$(ao beads dir)" br list --status open --json # All open issues
BEADS_DIR="$(ao beads dir)" br show <id> --json         # View issue details
BEADS_DIR="$(ao beads dir)" br update <id> --claim --json
BEADS_DIR="$(ao beads dir)" br close <id> --reason "Done"
BEADS_DIR="$(ao beads dir)" br sync --flush-only        # Export the git-JSONL ledger (never touches git itself)

Key Concepts

Issues: Atomic units of work
Dependencies: Issues can block each other
Session close: BEADS_DIR="$(ao beads dir)" br sync --flush-only after issue updates, then git -C "$(ao beads dir)" push to share the private ledger

What's NOT at This Level

No parallel execution
No /crank (autonomous execution)

Next Level

Once comfortable with issue tracking, progress to L4-parallelization to execute waves.

1.7 KiB Raw Blame History