reviewing-plans
Skill1 starsChanged 3 months agoMITView on GitHub
Gets an independent review of one exact plan version before the plan is presented for approval. Use when a written plan's route is high-risk and it is about to be shown for approval, or when the user says review this plan, is the plan sound, or check the plan before I approve it. Skip a plan whose files are not written yet, and skip editing the plan.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- seanmcgary/claude-skillstheir own version, first seen Nov 11, 2026
- kmorgan-r/claude-skillstheir own version, first seen Oct 22, 2026
- kskonovalov/claude-skillstheir own version, first seen Jul 29, 2026
- tunahanaliozturk/ateliertheir own version, first seen Jun 20, 2026
- wedow/skillstheir own version, first seen Mar 21, 2026
- chrispangg/super-rpitheir own version, first seen Mar 10, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- wedow/skills★ 8same name
- chrispangg/super-rpi★ 5same name
- kmorgan-r/claude-skills★ 1same name
- ogu8/reviewing-plans★ 1same name
- tunahanaliozturk/atelier★ 1same name
- kskonovalov/claude-skills★ 0same name
- seanmcgary/claude-skills★ 0same name
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 repository50 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- working-from-a-ticketSkill
- writing-specsSkill
- clarifying-intentSkill
- dispatching-parallel-agentsSkill
- handoffSkill
- mapping-the-codebaseSkill
- prototypingSkill
- runtime-evidenceSkill
- using-git-worktreesSkill
- using-sdlc-skillsSkill
- viewing-artifactsSkill
- writing-skillsSkill
- yagniSkill
- finishing-a-branchSkill
- release-readinessSkill
- architecture-decisionsSkill
- coding-standardsSkill
- data-modelSkill
- migration-strategySkill
- system-architectureSkill
- ui-ux-designSkill
- writing-plansSkill
- adding-observabilitySkill
- changing-a-live-schemaSkill
- executing-plansSkill
- rollout-controlsSkill
- subagent-driven-developmentSkill
- test-driven-developmentSkill
- complexity-auditSkill
- containing-an-incidentSkill
- debuggingSkill
- deprecating-an-apiSkill
- diagnosing-a-sessionSkill
- eliminating-correctionsSkill
- large-scale-changesSkill
- post-mortemSkill
- refactor-architectureSkill
- brainstormingSkill
- define-goalsSkill
- feasibility-checkSkill
- scopingSkill
- receiving-code-reviewSkill
- requesting-code-reviewSkill
- reviewing-a-prSkill
- security-auditsSkill
- verification-before-completionSkill
- verification-strategySkill
- visual-ui-verificationSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 3 are distinctive, and 7 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 25
If the caller is writing-plans presenting a plan whose route is not high-risk, ask the offer question below.
- Very specific: line 28
Ask it with the version plan-version.sh prints:
- Very specific: line 39
Ask this and end the turn.
- Distinctive: line 40
If the answer is option 1, go to Step 1.
- Very specific: line 60
If a predecessor version already has a review, bind that report too.
- Very specific: line 75
If the action is unavailable, refused, or comes back empty, write not dispatched and ask the not-dispatched question from …
- Distinctive: line 94
Read the report at the current attempt's location, opening the file when only its location came back and writing it there first when it …
- Very specific: line 123
If a blocker is accepted, return to the caller's pending step.
- Distinctive: line 127
If no blocker is open, return to the caller, or to the user who asked.
- Very specific: line 131
Never re-enter writing-plans or start an executor from here.
“Common” is measured: kept by at least 6 in 10 of the 5 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
Reviewing Plans
This skill never edits the plan, approves it, or starts an executor.
When to use
- A plan directory is written and about to be presented for approval, and its
classification route is high-risk:
writing-plansrequires this review. - The user asks for an independent look at a plan, or accepts the review that
writing-plansoffers for a plan that is not high-risk. - An executor proposes a high-risk successor mid-run (Step 1.6).
- Skip a plan with no printed version yet: its index or task files are not written.
- Skip editing the plan. Corrections belong to the plan's author, as a successor version.
- Skip a frozen code change;
requesting-code-reviewreviews that.
Step 0: The offer, for a plan that is not high-risk
- If the caller is
writing-planspresenting a plan whose route is not high-risk, ask the offer question below. If the user asked for the review directly, or the route is high-risk, skip Step 0 and go to Step 1. Ask it with the version
plan-version.shprints:Plan {{version}} is not high-risk. 1. Review it independently before presenting it 2. Present it without a review Recommendation: {{option}} — {{one sentence}}.Ask this and end the turn;
clarifying-intentowns what closes it.- If the answer is option 1, go to Step 1. If it is option 2, return to the caller, which presents the plan without a review.
Step 1: Bind the version, the inputs, and the reviewer
- Print the plan's version with the
plan-version.shscript thatwriting-plansships, run on the plan directory. If the script fails, name its error and stop; a version read from the index is not a version. - Bind every approved input the index's
Bound inputsline names, at the exact identity it names. An input missing at that identity is a finding for the author; never review against a newer one instead. - Bind one reviewer role ID that did not write this plan. Pick its tier with
the Model selection section of
dispatching-parallel-agents. - Bind the review boundary: read-only access to the plan directory, its
inputs, and the repository at the
Bound inputscode revision, the worker, provider, storage, and egress authority the user or project already gave, a deadline, and who cancels. If there is no such authority, the review is not dispatched (Step 2.3). - Bind the report location in the plan's evidence directory:
.sdlc-skills/evidence/{{plan directory name}}/00-index.review-{{version}}-{{attempt}}.md, attempt1first. It is the only path that attempt's reviewer may write. - If a predecessor version already has a review, bind that report too; the
new review reads the successor's delta (its
Successor deltaline, the tasks it adds or changes) and every section that depends on them, nothing else, and carries the earlier recorded decisions forward. An executor proposing a successor mid-run comes here the same way: the delta is reviewed, the approved remainder is not reread.
Step 2: Dispatch the review and keep its receipt
- Open
assets/plan-reviewer.mdafter Step 1 is bound. Fill every Inputs slot with the paths and identities from Step 1, never a paraphrase. - Send the filled prompt once through the harness's real dispatch action,
as
dispatching-parallel-agentsStep 2 says. Record the tool-issued ID as the dispatch receipt, with the plan version it binds. A name or a prompt is not a dispatch. - If the action is unavailable, refused, or comes back empty, write
not dispatchedand ask the not-dispatched question fromdispatching-parallel-agentsStep 2.2. A high-risk route requires an independent reviewer: omit its self-review option and say why. With no answer, the review stays pending. - Poll that receipt until the deadline. Never say a review is running without a receipt.
- On a failure, a timeout, or a cancellation, the review stays pending. This skill may retry once, through a new receipt linked to the failed one and a report location with the next attempt number, after correcting the cause that attempt named; a late result from the failed attempt, or a file at its path, is rejected. On a second failure, return the pending review and both receipts to the caller.
NEEDS_CONTEXTis not a failure and does not use that retry; Step 3.1 handles it. Its rerun happens once, at the next attempt number; a secondNEEDS_CONTEXTreturns to the caller as blocked, with its question.
Step 3: Receive the report, decide each finding, return
- Read the report at the current attempt's location, opening the file when
only its location came back and writing it there first when it came back
inline. If its
Plan versiondiffers from the bound version, or the report is missing or unreadable, the review stays pending. If the reviewer returnedNEEDS_CONTEXTwith a question, the review stays pending; return that exact question to the plan's author, at the caller's pending step (writing-plansStep 3.11, or the executor step that proposed the successor). A high-risk plan is not presented until the question is answered and the review is run again on the answered version. - Print the plan's version again. If it changed during the review, the review is void; report the edit to the caller and keep the review pending.
- Give every finding one recorded decision (the report calls these its
dispositions):
accepted: the author corrects it in a successor version.rejected: record the path and symbol or the command result that refutes it; an argument alone makes it adecision.decision: the index'sApproval ruleowner decides it, at presentation.- A finding that cites no task ID, section, or
path:line: record it asnot a finding: uncited.
- The report is the review record. Write into its header the dispatch
receipt, the report path, every recorded decision, who decided each, and
the date. Write no row in the plan's decision ledger: the plan's
presentation and its later approval row cite the report path in
Bound evidence. - Return to the caller's pending step with the report path and its recorded
decisions:
- If a blocker is
accepted, return to the caller's pending step; the correction is a proposed successor, and a high-risk successor comes back here before it is presented. That re-review is the last: a blocker it still raises is recorded as adecision. - If no blocker is open, return to the caller, or to the user who asked.
- On a high-risk route, the caller presents nothing until this review has returned and every blocker has a recorded decision; a pending or void review holds the presentation.
- If a blocker is
- Never re-enter
writing-plansor start an executor from here.
Gotchas
- A review that reads only the plan and its inputs checks the plan against
itself: nine such reviews passed a plan whose tasks could not be built as
written on the base they were bound to. The Buildability lens opens the
code, and a reviewer given no code revision returns
NEEDS_CONTEXT. - Self-review is not this review. The author's own checks in
writing-plansStep 3 read the plan with the assumptions that wrote it; counting them as the independent review presents a high-risk plan no second reader saw. - A reviewer that edits the plan voids the review: the version it read no longer exists, and its findings describe text nobody approved. Step 3.2 catches it by printing the version again.
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.

