review-plan
Skill0 starsChanged 20 days agoMITView on GitHub
Use when a plan in docs/plans/ is drafted and needs checking before any code ("review the plan", "is this plan ready", start-work's review step). A fresh reviewer applies REVIEW.md and lenses.md, refutes each finding and reports only real defects with their scenario, plus improvements; the round is written into the plan's Plan review section; another round only after a blocker or a major.
37 other projects use a version of this.
Adopted by
Most recently taken up by
- event-driven-io/emmetttheir own version, first seen Nov 16, 2026
- nicosocoro/agent-skillstheir own version, first seen Nov 15, 2026
- atomicinnovation/acceleratortheir own version, first seen Nov 14, 2026
- CsHeng/agent-skillstheir own version, first seen Nov 9, 2026
- withpiper/pipekittheir own version, first seen Nov 8, 2026
- mab-go/xmind-mcptheir own version, first seen Nov 8, 2026
Used with
Projects with it also use implement-plan, review-design 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.
JasonPaffSkillimplement-plan
Execute implementation plan with structured tracking and validation using subagent architecture
Also in 5 projects that use this
dirkkok101Skillreview-design
Use before /plan, after /technical-design, when user says "review design", "check the design", or when design quality is uncertain.
Also in 3 projects that use this
SvampenSkillreview-implementation
Reviews implementation against session/work stream goals before committing. Identifies shortcuts, hacks, incomplete work, and validates accomplishments match actual changes. Use before /session-end to ensure implementation quality.
Also in 3 projects that use this
PydanticSkillreview-security
Security review of the current branch against its merge base — sandbox escapes, memory errors, panics and resource-limit bypasses. Use when reviewing changes for security risk, or before merging anything touching the heap/ module, path_security.rs, the wire protocol or the pool.
Also in 3 projects that use this
am-willSkillplanner
Create comprehensive, phased implementation plans with sprints and atomic tasks. Use when user says: "make a plan", "create a plan", "plan this out", "plan the implementation", "help me plan", "design a plan", "draft a plan", "write a plan", "outline the steps", "break this down into tasks", "what's the plan for", or any similar planning request. Also triggers on explicit "/planner" or "/plan" commands.
Also in 3 projects that use this
sahinSkillexecute
Also in 3 projects that use this
Other versions37 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 37
- penpot/penpot★ 62ksame name
- event-driven-io/emmett★ 567same name
- JetBrains/youtrackdb★ 443same name
- wallstop/unity-helpers★ 177same name
- shader-slang/slangpy★ 157same name
- fitlab-ai/agent-infra★ 88same name
- microsoft/vscode-team-kit★ 67same name
- DasDigitaleMomentum/opencode-processing-skills★ 60same name
- Cleveland-RD/hivehouse★ 46same name
- atomicinnovation/accelerator★ 35same name
27 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- finish-workSkill
- review-codeSkill
- start-workSkill
- write-skillSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 36 edited versions we read keep these.
3
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
- Very specific: line 21
Review: Start one fresh agent, one that has not seen this session, with the plan's path, the ground-truth list and lenses.md (this folder).
- Distinctive: line 27
No agents in your tool: apply every lens yourself, then refute each finding, and say in the record that the author reviewed their own plan.
- Distinctive: line 39
Another round only after a blocker or a major: Commit the edits and go back to step 3: a fresh reviewer reads the edits and the open …
- Distinctive: line 48
Every owner call and every improvement has its answer.
“Common” is measured: kept by at least 6 in 10 of the 36 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.
Files
Review a plan
A plan review catches a design defect while it is still a one-line edit. Not a hunt: a finding is a defect that would
really hurt if the plan were followed as written (REVIEW.md, What a finding is), and most are minor.
Steps
- The plan, by path:
docs/plans/<date>-<slug>.md, never "the latest plan". Commit it first, so the round names a fixed version:git log -1 --format=%h -- <plan>. - The ground truth the reviewer reads:
AGENTS.md,REVIEW.md,docs/design.md, the plan in full, its issue (gh issue view <n> --comments), and every file and doc the plan names. - Review. Start one fresh agent, one that has not seen this session, with the plan's path, the ground-truth list
and
lenses.md(this folder). It reads and nothing else. It applies every lens, refutes each finding by quoting the plan and the rule or code, and returns the confirmed and refuted findings, each with its scenario and an honest severity, the improvements worth making, and a verdict. Don't read the ground truth into this session yourself.- Each confirmed blocker or major goes to its own fresh refuter agent, in parallel. One that can't settle it leaves the finding open, never refuted.
- No agents in your tool: apply every lens yourself, then refute each finding, and say in the record that the author reviewed their own plan.
- Write the round into the plan's "Plan review" section as
### Round <n>:- How: the reviewer, the model, the date; Verdict:; Now: what has been applied.
- A table
| # | Sev | Finding | Status |: idsP1,P2, ... numbered on across rounds, the finding with its scenario, statusopen,fixed(what changed), orwontfix: <why>. - Refuted findings under "Refuted", each with its reason.
- Owner calls, when there are any:
| # | Question | Recommendation | Answer |, idsQ1,Q2, ... - Improvements, each with its answer:
taken,left: <why>orlater: <issue>.
- Act. Edit the plan for each confirmed finding that keeps its design and scope, and mark it
fixed. One that changes either goes to the maintainer as a yes or no question with your recommendation, as an owner call. List the improvements to the developer and ask take, leave or later for each. - Another round only after a blocker or a major. Commit the edits and go back to step 3: a fresh reviewer reads the edits and the open findings only. Only minors: fix or record them, and the loop ends.
- Verdict:
approvedwhen no blocker or major is open, every owner call has its answer, and the plan names its tests and docs and ends withreview-code. Otherwiseneeds-fixesorneeds-answers. Commit the plan.
Done means
- The plan's "Plan review" section says
approved, or the maintainer stopped the loop with the open findings recorded. - Every owner call and every improvement has its answer.
Never
- Report a finding without its scenario, or inflate a minor to keep the loop going.
- Change the plan's design or scope without the maintainer's yes.
- Approve a plan with an open blocker on a command line, a one-way door or the harness.
- Drop a finding silently: refuted and
wontfixones stay in the plan.
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
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.

