plans
Skill24 starsChanged 57 days agoMITView on GitHub
Use for planning, roadmaps, design, architecture, sequencing, or before consequential work when no current FINAL plan plus GO covers it. Fire before changes to data or schemas, credentials or auth, production or releases, repository or source-home boundaries, irreversible work, or materially costly mistakes. Re-enter when that scope appears mid-task or when restoring prior plan state. Skip factual answers, trivial reversible one-step work, and authorized Builder or Reviewer execution under a current FINAL blueprint plus GO unless a reopen condition fires.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- futex-ai/skillstheir own version, first seen Oct 25, 2026
- PanPanFR/oh-my-openkilotheir own version, first seen Oct 22, 2026
- agentstation/skillstheir own version, first seen Oct 13, 2026
- Ezra144israel/governed-agent-skillsword for word, first seen Sep 17, 2026
- code-katz/claude-plans-skilltheir own version, first seen Jul 4, 2026
- brettatoms/agent-skillstheir own version, first seen Jan 30, 2026
Other versions6 projects use a version of this.
Word for word · 1
- Ezra144israel/governed-agent-skills★ 24100% same
Edited · 0
None found.
Wrote their own version · 5
- PanPanFR/oh-my-openkilo★ 9same name
- brettatoms/agent-skills★ 3same name
- agentstation/skills★ 1same name
- futex-ai/skills★ 1same name
- code-katz/claude-plans-skill★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- better-codingSkill
- ship-or-fixSkill
- teamworkSkill
- test-the-testSkill
- thinkingSkill
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 5 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Keep a compact Plan Capsule, not the planning transcript, for material work.
- Very specific: line 34
Add SOURCE HOME, BOUNDARIES, or OPEN only when they carry load-bearing information.
- Distinctive: line 53
Do not persist those temporary sections after the operator has seen them.
- Distinctive: line 65
Before continuing restored planning or execution:
- Very specific: line 68
Verify that AS OF includes the current operator instruction.
- Distinctive: line 71
If the capsule is complete, exact, and current, continue after the readback.
- Very specific: line 73
If state is incomplete, stale, conflicting, uncertain, or cannot reproduce the complete capsule exactly, mark RESTORED: UNVERIFIED, show …
- Distinctive: line 79
When the operator settles the plan, respond exactly:
- Very specific: line 87
When a FINAL plan is handed to a Builder or Reviewer, read references/blueprint.md.
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Plans
Keep a compact Plan Capsule, not the planning transcript, for material work.
Plan Capsule
PLAN <id>: DRAFT | CHALLENGE-READY | FINAL
AS OF <latest operator instruction accounted for>
DEPTH: LIGHT | STANDARD | DEEP
ASKED
<operator's words that define the outcome>
GOAL
<accepted restatement>
DELIVERABLE
<what will exist>
PLAN
1. <step with a checkable completion condition>
2. <step with a checkable completion condition>
DONE
<smallest observable acceptance condition>Add SOURCE HOME, BOUNDARIES, or OPEN only when they carry load-bearing information.
Copy ASKED from the operator. A continuation (proceed, yes) keeps ASKED and advances AS OF. A changed outcome replaces ASKED, updates the plan, and is read back.
Readback
Show the full current capsule when a load-bearing part of the plan changes, before challenge, on restore, and before final closeout. Append only applicable temporary sections:
CHANGED
- <changed plan state>
ADDED
- <new agent-added scope or requirement>
DROPPED
- <operator-requested item that disappeared or changed meaning>Do not persist those temporary sections after the operator has seen them.
Depth and challenge
LIGHT: bounded, familiar, reversible work. No challenge by default.STANDARD: several meaningful decisions or moderate uncertainty. Challenge when a load-bearing question remains, the operator asks, or error cost warrants it.DEEP: architecture, broad blast radius, authority, safety, recovery, migration, expensive error, or major uncertainty. Challenge by default unless the operator skips it.
Raise depth when stakes rise. Read back every depth change.
Restore
Before continuing restored planning or execution:
- Reproduce the latest complete capsule.
- Verify that
AS OFincludes the current operator instruction. - Show the capsule readback before any mutation or execution.
If the capsule is complete, exact, and current, continue after the readback. Do not ask for another confirmation only because a session boundary occurred.
If state is incomplete, stale, conflicting, uncertain, or cannot reproduce the complete capsule exactly, mark RESTORED: UNVERIFIED, show the reconstruction, and hold for operator confirmation. A FINAL blueprint plus GO is not an exact restore when the complete capsule cannot be reproduced.
Final and GO
Ask: Is this the plan?
When the operator settles the plan, respond exactly:
Plan is FINAL. Execution waits for your GO.
FINAL never authorizes execution. Execute only after a later, separate, explicit GO.
Downstream blueprint
When a FINAL plan is handed to a Builder or Reviewer, read references/blueprint.md. Reopen planning before changing the objective, deliverable, source home, load-bearing boundary, acceptance condition, or plan currency.
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.

