agentleFS
iwe-orgiwe-org/dev-workspace/.claude/skills/plan/SKILL.md

plan

Skill11 starsChanged 2 days agoMITView on GitHub

Create an implementation plan — discovery in the real codebase first, then a plan document with verified code anchors, spec impact, and dependencies, filed under Active in the plans hub. Use when the user says "plan <feature>", "write a plan for ...", or asks to turn a backlog task or accepted feature into work.

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

3 rules. 0 are common, 0 are distinctive, and 3 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.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Consult: Read data/product.md — especially ## Constraints and ## Authoring rules, which bind what you write.

    line 14
  2. Very specific:

    Discover: Read the code the plan will touch.

    line 19
  3. Very specific:

    File it: Add an inclusion link under ## Active in data/plans.md, and under the phase it advances in its milestone plan if one schedules it, …

    line 52

“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 a piece of work

A plan is a promise a future session can execute without re-deriving context. Discovery happens in the codebase before a word is written; every anchor is verified, every touched spec is named.

Steps

  1. Consult. Read data/product.md — especially ## Constraints and ## Authoring rules, which bind what you write. Check for related work: iwe find --fuzzy <topic> -f keys, the relevant data/spec/ and data/features/ docs, and whether an active plan already covers this (iwe find --included-by data/plans -f keys).
  2. Discover. Read the code the plan will touch. Collect the entry points, the functions to modify, and their current line numbers — these become ## Key references, and they must come from the current checkout, not memory.
  3. Create. iwe new "<Title>" --key data/plans/<YYYYMMDD>-<slug> --content "" (today's date, kebab slug; the title is required, and the empty --content keeps the command from waiting for piped input). It writes the # <Title> heading; add the frontmatter above it:

    ---
    type: plan
    created: <today>
    ---

    Body sections, in order (omit a section only when it's genuinely empty):

    • ## Context — why now, linking the feature/bug/backlog doc that motivates it
    • ## Approach — the shape of the solution and the alternative you rejected, in a few sentences
    • ## Implementation Steps — ### Task N: <name> blocks, each with **Files:** Create:/Modify: ... and - [ ] checkboxes
    • ## Spec changes — every data/spec/ doc this work will create or change; name not-yet-existing specs in back-ticks (never dangling links)
    • ## Depends on — inline links to plans that must ship first (omit if none)
    • ## Verification — how a session proves the work is done: commands, tests, manual checks
    • ## Out of scope — what this plan deliberately does not do
    • ## Key references — path:line — symbol list under a line Verified anchor points (line numbers as of <today>):
  4. File it. Add an inclusion link under ## Active in data/plans.md, and under the phase it advances in its milestone plan if one schedules it, with tags: [milestone-<slug>] in the plan's frontmatter. If the plan implements a proposed feature, accept the feature and clear the draft status that proposed carried: iwe update -k data/features/<slug> --set stage=accepted --unset status. If it grew from a backlog task, mark the task done (stage: done, completed) and move its link to ## Done in data/backlog.md. If it replaces an older plan, link the old plan from ## Context and cancel it in the same change (the ship skill's cancel path).
  5. Validate. iwe normalize, then iwe schema validate — must pass.

Rules

  • One plan per topic; if the plan needs two unrelated verification stories, it's two plans.
  • Code anchors are verified against the current checkout and stamped with the date — never cite from memory.
  • ## Spec changes is mandatory thinking, even when its honest content is "none — no behavioral change".
  • Scale ceremony with risk: a small low-risk plan can be short, but never skip Verification.

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.