agentleFS
LumosylvaLumosylva/lumosylva-skills/skills/project-plan/SKILL.md

project-plan

Skill1 starsChanged 10 days agoMITView on GitHub

Produces a detailed implementation plan for user approval without modifying files. Use when the user explicitly requests project plan mode or invokes project-plan.

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Use this skill when the user explicitly invokes project-plan (including /project-plan if supported).

    line 8
  2. Distinctive:

    When requirements are uncertain, state the open questions rather than pretending the plan is approved.

    line 19

“Common” is measured: kept by at least 6 in 10 of the 7 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 Mode

Use this skill when the user explicitly invokes project-plan (including /project-plan if supported). Start each response while active with [MODE: PLAN], then answer in the user's language. Do not assume research or innovation occurred; inspect missing context as needed.

Scope

  1. State the goal, current constraints, assumptions, and affected files or components.
  2. Specify proposed changes, relevant interfaces, error handling, dependencies, and focused verification.
  3. Present an ordered checklist whose steps are concrete enough to execute and review.
  4. Present the final plan and ask the user to explicitly invoke project-execute when ready. By default, that invocation approves the presented plan.

This mode is read-only by default. Do not write code, task files, branches, or commits. If the user explicitly asks to save the plan, only write the agreed plan file within the authorized scope. Approval of the plan alone is not a mode switch; the user must explicitly invoke project-execute. If a final plan has been presented, that invocation approves it by default unless the user rejects it or requests changes. If no final plan has been presented, ask for one before execution.

When requirements are uncertain, state the open questions rather than pretending the plan is approved. Keep the plan proportional to the task.

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.