thin-plan
Skill6 starsChanged 3 months agoMITView on GitHub
Convert a mini-spec into 3-7 vertical implementation slices.
In this repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- analyze-miniSkill
- bug-captureSkill
- build-oneSkill
- ceremony-budgetSkill
- checklist-miniSkill
- constitution-liteSkill
- context-checkSkill
- diagnose-loopSkill
- eco-modeSkill
- falsify-specSkill
- grill-with-docs-liteSkill
- handoffSkill
- lean-modeSkill
- mini-specSkill
- operator-profileSkill
- scope-freezeSkill
- ship-miniSkill
- teach-backSkill
- test-miniSkill
- tool-noise-guardSkill
- verify-contractSkill
- workspace-checkpointSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Use when SPEC.md exists and implementation needs a short, ordered path.
- Very specific: line 25
If SPEC.md has an active Contract ID, copy that ID exactly into PLAN.md.
- Distinctive: line 27
Create 3-7 slices that each produce observable behavior.
- Distinctive: line 29
Keep each slice to the fewest files possible.
- Distinctive: line 30
Avoid horizontal architecture-only tasks unless required.
- Very specific: line 32
Write PLAN.md and TODO.md.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Thin Plan
Purpose
Convert the mini-spec into 3-7 vertical implementation slices.
When to use
Use when SPEC.md exists and implementation needs a short, ordered path.
Inputs
SPEC.mdCONTEXT.md- Existing repo structure
- Available verification commands
Workflow
- If
SPEC.mdhas an active Contract ID, copy that ID exactly intoPLAN.md. Do not invent an ID when SPEC has none. - Identify the smallest end-to-end behavior.
- Create 3-7 slices that each produce observable behavior.
- Make every slice independently verifiable.
- Keep each slice to the fewest files possible.
- Avoid horizontal architecture-only tasks unless required.
- Record dependencies, risks, and verification strategy.
- Write
PLAN.mdandTODO.md.
Outputs
PLAN.mdTODO.md- Active Contract ID in
PLAN.mdonly when SPEC opted into contract identity
Stop conditions
- Each task has a visible result and a check.
- Planning reveals a missing spec decision.
Anti-patterns
- Planning all backend, then all frontend, then all tests.
- Creating broad tasks that cannot be finished in one session.
- Treating setup work as progress when no behavior changes.
- Inventing contract identity for work whose SPEC did not opt in.
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.