plan-it
CLAUDE.md1 starsChanged 2 months agoMITView on GitHub
Claude Code plugin: deterministic multi-squad planning pipeline (statechart core + gate-check + PreToolUse hard gate). Plugin source: plugins/plan-it/. Current: v5.1.2. Docs home: docs/ <!-- session-debrief writes here --> Conventions: brain-docs schema (type/title/description/status/verified/repos/tags frontmatter); legacy files gain frontmatter when next edited. The raw v3 field-study package (spec seed, FD-1/FD-2 mandates, brief, 8 findings reports, launch prompt) lives at the repo root but is git-ignored and local-only — it carries personal/project-identifying material and is deliberately not published. The public synthesis and its…
In this repositoryOne other file it gives its agents.
- plan-itSkill
The file
Files
plan-it
Claude Code plugin: deterministic multi-squad planning pipeline (statechart core + gate-check + PreToolUse hard gate). Plugin source: plugins/plan-it/. Current: v5.1.2.
Documentation
Docs home: docs/ <!-- session-debrief writes here -->
Conventions: brain-docs schema (type/title/description/status/verified/repos/tags frontmatter); legacy files gain frontmatter when next edited.
Research
The raw v3 field-study package (spec seed, FD-1/FD-2 mandates, brief, 8 findings reports, launch prompt) lives at the repo root but is git-ignored and local-only — it carries personal/project-identifying material and is deliberately not published. The public synthesis and its index live under docs/research/v3/ (docs/research/v3/index.md).
<!-- plan-it:test-conventions -->Runner: node tests/run-contract.mjs (zero deps; exit 0 only at 100% pass). Binding cases are discovered from the frozen CONTRACT's '## Cases' table (| ID | @tag | Case | run: |) — every row carries a run: command; enforcement rows must FAIL CLOSED against a violating fixture under tests/fixtures/<version>/. Per-case scripts live in tests/<version>/*.mjs; shared helpers in tests/<version>/lib/. gate-check verbs are exercised positionally and via --dir. Release gates: run-contract 100%, fail-closed-sweep, mirror-check 8/8, machine-diff additive vs pinned baseline, version-triple-match, changelog-shape. v4 adds tests/v4/ + tests/fixtures/v4/ in the same shape.
<!-- /plan-it:test-conventions -->Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.