agentleFS
Sign inStart free
roronoazoroshao369roronoazoroshao369/vibe-coding-os/skills/core/plan-driven-execution/SKILL.md

plan-driven-execution

Skill1 starsChanged 5 months agoMITView on GitHub

Convert a spec or task into small ordered implementation steps. Use before multi-file edits, refactors, migrations, or debugging sessions. Spec, repository map, constraints, verification requirements. A practical plan with task order, file targets, risks, and checks. Use with writing-plans for plan creation and executing-plans for plan execution. Related mattpocock-inspired skill: skills/core/issue-slicing/SKILL.md for independently grabbable vertical slices. Executing a written, approved plan checkpoint by checkpoint (fresh execution). If this skill is not the right phase for your task, use one of…

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    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. Distinctive:

    Use before multi-file edits, refactors, migrations, or debugging sessions.

    line 21
  2. Distinctive:

    Update the plan as facts change.

    line 33
  3. Very specific:

    Use with writing-plans for plan creation and executing-plans for plan execution.

    line 54
  4. Distinctive:

    If this skill is not the right phase for your task, use one of these instead:

    line 62

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Skill: Plan-Driven Execution

Purpose

Convert a spec or task into small ordered implementation steps.

When to use

Use before multi-file edits, refactors, migrations, or debugging sessions.

Inputs

Spec, repository map, constraints, verification requirements.

Workflow

  1. Identify files and components likely to change.
  2. Break work into small tasks.
  3. Order tasks by dependency and risk.
  4. Attach verification to each major step.
  5. Update the plan as facts change.

Outputs

A practical plan with task order, file targets, risks, and checks.

Failure modes

  • Plan is too vague to execute.
  • Plan ignores verification.
  • Plan is not updated after discoveries.

Verification checklist

  • Steps are ordered and concrete.
  • Risky areas are named.
  • Verification commands are included.
  • Scope remains aligned with the spec.

Superpowers alignment

Use with writing-plans for plan creation and executing-plans for plan execution.

Related mattpocock-inspired skill: skills/core/issue-slicing/SKILL.md for independently grabbable vertical slices.

Choose instead

Executing a written, approved plan checkpoint by checkpoint (fresh execution).

If this skill is not the right phase for your task, use one of these instead:

  • skills/core/executing-plans/SKILL.md — if work was started, paused, or context was lost (resumption).
  • skills/core/writing-plans/SKILL.md — if the plan does not yet exist or needs revision.

For the full decision tree across all 6 plan-family skills, see docs/workflows/plan-skill-decision-tree.md.

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