agentleFS
Sign inStart free
qyndexqyndex/claude-init/.claude/skills/plan/SKILL.md

plan

Skill2 starsChanged 5 months agoMITView on GitHub

Author the technical plan for a spec. Phase 3 of the eight-phase workflow. Produces plans/active/<id>-<slug>.md with architecture, data model, API contracts, dependencies, phasing, risks. Delegate to the architect agent. Modeled on github/spec-kit /speckit.plan.

184 other projects use a version of this.

Adopted by

Most recently taken up by

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-incSkill

    heartmula

    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-ywSkill

    webhook-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-incSkill

    minecraft-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-chenSkill

    touchdesigner-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

  • gaebalaiSkill

    codex-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

  • ibahgatSkill

    context-optimize

    Improve context efficiency and cache stability for long or complex sessions.

    Also in 3 projects that use this

  • +3 more from math-inc

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 168 edited versions we read keep these.

  • 2

    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
  1. Very specific:

    Mark status: approved: when complete.

    line 20
  2. Distinctive:

    Smallest viable design: Don't add abstractions for hypothetical needs.

    line 37
  3. Distinctive:

    Cite evidence: Every "we chose X because Y" must reference a doc, benchmark, or precedent.

    line 38
  4. Very specific:

    After save: "Plan plans/active/<id>-<slug>.md ready.

    line 49

“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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Plan

Turn an approved spec into an actionable technical plan.

Process

  1. Read the spec (specs/active/<id>-<slug>.md). Confirm status: approved.
  2. Delegate to the architect agent. They produce plans/active/<id>-<slug>.md.
  3. Review the plan for completeness against the template at plans/templates/plan.md.
  4. Validate against the spec — every acceptance criterion must map to plan elements.
  5. Mark status: approved when complete.

Plan must contain

  • Reference to the spec (spec: specs/active/<id>-<slug>.md)
  • Architecture — components, data flow, sequence diagrams (mermaid if non-trivial)
  • Data model — entities, schemas, migrations, indexes
  • API contracts — endpoints, request/response shapes, error codes, auth
  • Dependencies — new packages (with version + justification), new services, new MCP servers
  • Phasing — Phase 1, 2, 3 with exit criteria per phase; each phase must be independently shippable
  • Risks — known unknowns + mitigations
  • Rollback — how do we revert if Phase N is bad?
  • Observability — metrics, logs, traces this change adds
  • References — every non-obvious decision cites a doc/RFC/file/repo

Hard rules

  • Smallest viable design. Don't add abstractions for hypothetical needs.
  • Cite evidence. Every "we chose X because Y" must reference a doc, benchmark, or precedent.
  • Phases ship. Phase 1 alone should deliver value, not be "scaffolding".
  • Surface risks. A risk hidden is a risk multiplied.
  • Decisions become ADRs (gap-audit G39). Every non-obvious architectural choice in the plan gets an ADR: bash .claude/scripts/adr-new.sh "<title>" --by architect --subsystem <key>, then fill Context/Decision/Alternatives. The plan's References section must cite it. A plan whose References cite no ADR while making architecture choices is incomplete — validate.sh fails the repo when active plans exist with an empty decisions store.

Output

plans/active/<id>-<slug>.md   (status: draft → approved)

After save: "Plan plans/active/<id>-<slug>.md ready. <N> phases, <M> dependencies. Ready for /tasks."

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free