agentleFS
Sign inStart free
vidit19sharmavidit19sharma/neogents/skills/plan/SKILL.md

plan

Skill1 starsChanged 12 days agoMITView on GitHub

Run the DEEP planning flow — relentless requirements interview, then a reviewable plan artifact in .neo/plans/. Use for new features, ambiguous scope, architectural changes, or when the user says "plan this" or "let's think this through".

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

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

  • 0

    Common

    Most of the 167 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the codebase can answer it, explore it yourself (or fan out built-in exploration subagents) instead of asking.

    line 15
  2. Distinctive:

    Keep going until goal, scope, non-goals, constraints, and every fork in the road are resolved.

    line 17

“Common” is measured: kept by at least 6 in 10 of the 167 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

/neo:plan — interview, then plan artifact

Phase 1 — Interview (main thread, you)

Interview the user relentlessly about this work until you reach shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one by one.

Rules:

  • ONE question at a time. Never a questionnaire.
  • For every question, lead with your recommended answer and why.
  • If the codebase can answer it, explore it yourself (or fan out built-in exploration subagents) instead of asking.
  • Consult .neo/brain/DECISIONS.md and BRIEF.md first — never re-ask what's already decided.
  • Keep going until goal, scope, non-goals, constraints, and every fork in the road are resolved. "I don't know" from the user = you propose, they confirm.

Phase 2 — Plan artifact (you)

Write the plan artifact yourself to .neo/plans/YYYY-MM-DD-<slug>.md — first stop and tell the user if .neo, .neo/plans or that file is a symlink ([ -L ... ]): a clone can ship one pointing outside the repo, and the write would follow it. Write it following ${CLAUDE_PLUGIN_ROOT}/templates/plan.md: goal, non-goals, inherited decisions, task graph, waves, per-task files/do/verify/agent, risks. Carry the interview decisions and rationale into it — do not relitigate them, and do not leave open questions unstated.

Phase 3 — Approval gate

Present the plan summary: goal, wave schedule, task count, risks. Resolve any remaining open questions with the user and update the artifact before proceeding.

Do not execute until the user approves the plan. On approval, set the contract per task — you draft done-criteria and verify plan, smith objects ONCE with concrete gaps, you revise, the agreed contract is written into the plan artifact and handed to trinity as her spawn contract — then execute wave by wave: trinity per task (fresh context each, tests included), then strip slop and re-run tests, then smith after the final wave on the final diff against the recorded contracts. After two failed fixes on the same problem, stop and re-derive from scratch per the failure protocol.

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