agentleFS
Sign inStart free
IcodeNetIcodeNet/agent-skills/skills/plan-critic/SKILL.md

plan-critic

Skill0 starsChanged 4 months agoMITView on GitHub

Challenge a proposed implementation plan before execution: scope, dependency order, PR slicing, risk, test adequacy, operational readiness. Use when the user asks to review, critique, or stress-test a plan, or after plan-from-rfc when a second pass is wanted.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    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 missing, ask for:

    line 16
  2. Distinctive:

    Test adequacy (targeted tests, hotspot checks, missing integration/E2E)

    line 30
  3. Distinctive:

    Prefer minimal changes to make the plan executable.

    line 47
  4. Distinctive:

    If the plan is already solid, say so and keep only minor improvements.

    line 49

≈ “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

Plan Critic

Challenge an implementation plan before anyone executes it.

Input collection

If missing, ask for:

  1. Plan text to review (required)
  2. Source document (RFC URL/path) if available
  3. Constraints (time, risk tolerance, no-behavior-change, testing limits)

Review checklist

Evaluate and report on:

  1. Scope clarity (in/out, non-goals, hidden expansion risk)
  2. Dependency order (technical and process dependencies)
  3. PR slicing quality (too broad, too coupled, conflict-prone)
  4. Risk coverage (runtime regressions, migration risk, rollback viability)
  5. Test adequacy (targeted tests, hotspot checks, missing integration/E2E)
  6. Decision traceability (explicit decisions vs assumptions)
  7. Operational readiness (release approach, feature flags, observability/support)
  8. Contract safety (does any step change an externally consumed surface without the contract-guard treatment?)

Output format (exact order)

  1. Verdict (Go, Go with changes, or No-go)
  2. Critical Gaps (must-fix)
  3. Important Improvements (should-fix)
  4. Revised PR Sequence (if needed)
  5. Minimum Test Gate
  6. Approval Questions

Rules

  • Be direct and evidence-based.
  • Prefer minimal changes to make the plan executable.
  • Flag assumptions explicitly.
  • If the plan is already solid, say so and keep only minor improvements.

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