agentleFS
Tsurai7Tsurai7/agentic-playbook/skills/plan-review/SKILL.md

plan-review

Skill0 starsChanged 4 months agoMITView on GitHub

Engineering review of an implementation plan before any code is written: scope challenge first, then architecture, code quality, tests, performance. Use when asked to review/critique a plan, design doc, or proposed approach, or before approving a multi-file implementation plan. Skip for reviewing a code diff (staff-review), for deciding whether the idea is worth building at all (office-hours), and for single-step plans with an obvious shape.

43 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use plan-execute, pr-comment and 9 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.
  • longranger2Skill

    plan-execute

    Use when the user says "/plan-execute", "plan execute", "implement plan", or "execute plan" and provides a finalized plan file path to carry out. Claude orchestrates, Codex writes code, Claude reviews, and Codex fixes issues until the quality bar is met.

    Also in 3 projects that use this

  • BenjaminGSkill

    pr-comment

    This skill should be used when reviewing someone else's pull request and you want drafted review comments posted to GitHub — either gate / gate-wf findings (tier-marked) or pr-challenge's reviewer questions (unmarked) — each drafted through humanizer and posted as a standalone inline comment at its file:line, after one confirmation. Triggers on "post these as review comments", "comment the gate findings on the PR", "draft and post my review", "leave review comments", after a gate / gate-wf run or a pr-challenge pass on a PR you're reviewing.

    Also in 3 projects that use this

  • MicrosoftSkill

    spec-review

    Independent, multi-model review of a design or spec **before** any code is written, for the microsoft/winappcli repo. Activate when a contributor asks to "review this spec", "review my design", "review this design doc", "validate this approach", "should we build this", "spec review", "design review", or "feature review". Fans out parallel sub-agents — each doing its OWN research against the real codebase and ecosystem rather than trusting the spec — covering necessity & scope, approach & alternatives, feasibility vs reality, risks & unknowns, DX & user impact, and a different-model-family cross-check. Emits a decision-oriented recommendation (proceed / proceed-with-changes / reconsider) to stdout. This is the PRE-CODE companion to the pr-review skill (which reviews code already written); use spec-review at the design/spec stage, not on an implemented diff. Does NOT write code or edit the spec.

    Also in 3 projects that use this

  • AWSSkill

    retro

    Conduct a retrospective on a coding session.

    Also in 5 projects that use this

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 5 projects that use this

  • asterkinSkill

    adr

    Create Architecture Decision Records (ADRs) following project standards. Guides template usage, process, and best practices for documenting architecturally significant decisions.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 35 edited versions we read keep these.

  • 1

    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:

    Prefer capturing outputs from existing flows over building parallel ones.

    line 23

“Common” is measured: kept by at least 6 in 10 of the 35 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 review

Confirm the target

Name what is being reviewed (which plan, solving what problem) and the goal it serves before critiquing. If the idea itself is unvetted, run office-hours first — a plan review sharpens a plan; it cannot justify one.

Step 0: scope challenge (before any section review)

  1. Reuse first — what existing code already solves each sub-problem? Prefer capturing outputs from existing flows over building parallel ones.
  2. Minimum change set — flag anything deferrable without blocking the goal.
  3. Complexity smell — more than ~8 files touched or 2 new classes/services: stop and challenge whether fewer moving parts reach the same goal. Propose the minimal version; let the owner decide.
  4. Built-in over custom — for each new pattern or component, check whether the framework/runtime ships one before accepting a hand-rolled version.
  5. No silent drops — deferred work (distribution, ops, migrations) goes in an explicit "NOT in scope" list, not out of memory.

Once the scope decision is made, commit to it — do not re-argue scope during the section reviews below.

Section review

Work in order, at most ~8 top issues total across sections: Architecture → Code quality → Tests → Performance. For tests, demand a verifiable check per plan step — a plan step without its proving command is a wish (see verification-before-completion).

Judgment instincts to apply throughout

  • Blast radius — worst case, and how many systems/people it touches.
  • Boring by default — innovation tokens are scarce; proven tech elsewhere.
  • Incremental over big-bang — strangler fig, canary, refactor-then-change.
  • Reversibility — flags and staged rollouts make being wrong cheap.
  • Essential vs accidental complexity — is this solving a real problem or one the plan created?

End with a verdict: approve / reduce scope / rework, with the blocking items.

Provenance

Distilled from the gstack /plan-eng-review skill by Garry Tan (garrytan/gstack, MIT) — method only, none of the runtime (no brain preflight, design-doc discovery, or interactive scaffolding carried over).

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.