plan
Skill4 starsChanged 3 months agoMITView on GitHub
Interactively plan a feature with the user, then land it as right-sized build-ready tasks: one spec handed straight to /build, or dependency-ordered backlog issues. Use when the user says "plan X", "break down X", "create issues for X", or brings an idea too large for a single /build task.
184 other projects use a version of this.
Adopted by
Most recently taken up by
- event-driven-io/emmetttheir own version, first seen Nov 16, 2026
- champ18ion/claud18codetheir own version, first seen Nov 16, 2026
- FAHTHIZ/oasistheir own version, first seen Nov 16, 2026
- chuckplayer/claude-agent-packtheir own version, first seen Nov 16, 2026
- ansvisor/ansvisortheir own version, first seen Nov 15, 2026
- timmo001/skillstheir own version, first seen Nov 15, 2026
Used with
Projects with it also use heartmula, webhook-subscriptions and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
math-incSkillheartmula
Set up and run HeartMuLa, the open-source music generation model family (Suno-like). Generates full songs from lyrics + tags with multilingual support.
Also in 9 projects that use this
Tommy-ywSkillwebhook-subscriptions
Create and manage webhook subscriptions for event-driven agent activation, or for direct push notifications (zero LLM cost). Use when the user wants external services to trigger agent runs OR push notifications to chats.
Also in 5 projects that use this
math-incSkillminecraft-modpack-server
Set up a modded Minecraft server from a CurseForge/Modrinth server pack zip. Covers NeoForge/Forge install, Java version, JVM tuning, firewall, LAN config, backups, and launch scripts.
Also in 5 projects that use this
john-data-chenSkilltouchdesigner-mcp
Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.
Also in 6 projects that use this
gaebalaiSkillcodex-system
PROACTIVELY consult Codex CLI, your highly capable supporter with exceptional reasoning and task completion abilities. Codex is a trusted expert you should ALWAYS consult BEFORE making decisions on: design choices, implementation approaches, debugging strategies, refactoring plans, or any non-trivial problem. When uncertain, consult Codex. Don't hesitate - Codex provides better analysis. Explicit triggers: "think deeper", "analyze", "second opinion", "consult codex".
Also in 3 projects that use this
ibahgatSkillcontext-optimize
Improve context efficiency and cache stability for long or complex sessions.
Also in 3 projects that use this
- +3 more from math-inc
Other versions184 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 184
- Yeachan-Heo/oh-my-codex★ 34ksame name
- crbnos/carbon★ 2.8ksame name
- graphistry/pygraphistry★ 2.6ksame name
- zereight/gitlab-mcp★ 2.1ksame name
- math-inc/OpenGauss★ 1.3ksame name
- kdlbs/kandev★ 1.1ksame name
- suboss87/FDEOps★ 940same name
- codewithmukesh/dotnet-claude-kit★ 808same name
- witnesstodark/mr-mak-workspace★ 800same name
- loongclaw-ai/loongclaw★ 640same name
174 more not listed
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 repository5 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- buildSkill
- commitSkill
- pmSkill
- setup-stackSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 168 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 30
If it is one task: write the single spec and hand it to /build (or the agent label).
- Very specific: line 36
When the spread of issues makes progress hard to read, group them under a milestone and assign every issue to it.
“Common” is measured: kept by at least 6 in 10 of the 168 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
/plan: from idea to build-ready work
Input ($ARGUMENTS): a feature or project description, however rough.
Outcome: a plan the user has explicitly approved, expressed as right-sized, build-ready tasks the inner loop can consume one at a time. The quality bar is high on purpose: first-pass quality is the dominant predictor of loop output (see docs/DESIGN.md), and the spec is where first-pass quality is decided.
1. Understand before proposing
Interview the user, as many rounds as it takes, until you can state without guessing: the goal and why now, the user-visible behavior, constraints (stack, compatibility, performance, security), what is explicitly out of scope, and how success is verified. The plan must be grounded in the codebase as it actually is, not as assumed. Challenge vague answers instead of absorbing them: "proper auth" is not a requirement; "email+password login with session cookies, no OAuth yet" is. Surface the decisions the user hasn't realized they're making.
2. Propose, then iterate to approval
Present the plan: approach, decomposition, ordering with dependencies, and open risks. Iterate until the user explicitly approves. Create nothing before approval.
Size tasks by cohesion. One task is a chunk an implementer can carry to a coherent, finished state and a human can still review in one sitting; it leaves the app releasable and is verifiable on its own. Splitting costs a spec, a branch, a review loop and a merge, and the seams are where incoherence enters, so a split needs a reason — typically:
- a hard dependency (one task's output is another's input),
- a risky unknown worth landing on its own, so it can be judged or reverted in isolation,
- a diff a human could no longer review honestly in one pass.
A coherent surface — a page, a user flow, a design system, a resource end-to-end — is the natural unit: build it whole while the diff stays reviewable. Slicing a UI by section is the classic failure, five PRs that each pass review and together look like five different products; when a surface genuinely outgrows one task, split it so the design is still decided once — its foundation lands first and later tasks conform to it.
3. Land the plan
If it is one task: write the single spec and hand it to /build (or the agent label). No issues needed.
If it is several:
- One issue per task in the PM spec format (goal, acceptance criteria, out of scope, verification plan).
gh issue createwhen a remote exists; BACKLOG.md sections otherwise. - Label issues whose prerequisites aren't merged yet
blocked, with "Blocked by #N" in the body. - When the spread of issues makes progress hard to read, group them under a milestone and assign every issue to it.
ghhas no milestone command; create it withgh api, putting the ordering and rationale in its description. - Report what was created and offer the first dispatch:
/buildon the first task, or theagentlabel to run it in CI.
How many issues that comes to is whatever the split triggers produce. When the later phases of a plan are still speculative, detail the near-term tasks fully and leave the rest as coarser placeholders; a future /plan run refines them when their turn comes.
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.

