review-loop
Skill18 starsChanged 52 days agoApache-2.0View on GitHub
Drive the local pre-push review loop to settle — absorb findings locally before any external bot pass
61 other projects use a version of this.
Adopted by
Most recently taken up by
- MichaelHolley/cc-pluginstheir own version, first seen Nov 16, 2026
- tunnckoCore/skillstheir own version, first seen Nov 16, 2026
- DaraBoth/skilljmskilltheir own version, first seen Nov 15, 2026
- agentcrew-academy/harness-starter-kittheir own version, first seen Nov 15, 2026
- sp-hk2ldn/SKILLStheir own version, first seen Nov 15, 2026
- HerbertGao/herbertgao-skillstheir own version, first seen Nov 15, 2026
Used with
Projects with it also use motion-design, polish and 10 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.
soilmassSkillmotion-design
Create animations and motion graphics using industry standards. Use when asked to animate UI elements, create video content, implement transitions, or build motion systems. Implements W3C Design Tokens, Material Design 3 baseline, and Lottie specification compliance.
Also in 5 projects that use this
HK-hubSkillpolish
Performs a final quality pass fixing alignment, spacing, consistency, and micro-detail issues before shipping. Use when the user mentions polish, finishing touches, pre-launch review, something looks off, or wants to go from good to great.
Also in 3 projects that use this
GoogleSkillto-spec
Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.
Also in 4 projects that use this
GoogleSkillimprove-codebase-architecture
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
Also in 5 projects that use this
AWSSkillship
Finalize dev work on an issue branch — update docs, push, and open a PR.
Also in 4 projects that use this
MicrosoftSkillcouncil
Convene the persona panel — six orthogonal review lenses — on a target. Cold independent fan-out, debate-to-consensus, synthesized verdict with recorded dissent and a roster manifest.
Also in 3 projects that use this
- +4 more from google
Other versions61 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 61
- didi/mpx★ 4ksame name
- blockscout/frontend★ 310same name
- microsoft/bocpy★ 184same name
- 9thLevelSoftware/legion★ 76same name
- microsoft/Trieste★ 53same name
- revisit-studies/study★ 46same name
- timharris707/skills★ 44same name
- agentcrew-academy/harness-starter-kit★ 42same name
- spxrogers/agentsync★ 41same name
- Latand/delegatus★ 39same name
51 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 repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- review-replySkill
- signoffSkill
- signonSkill
- postmergeSkill
- preflightSkill
- prepushSkill
- review-loopSkill
- review-replySkill
- signoffSkill
- signonSkill
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 54 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
- Distinctive: line 25
A degraded round is never settled: If completed < attempted (a lane failed), the round did not settle — say so.
“Common” is measured: kept by at least 6 in 10 of the 54 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
<!-- totem:skill-start -->Drive the LOCAL pre-push review loop to convergence: run the review, absorb its findings, re-run, and repeat until the CLI reports the round settled — before any external bot pass. The loop state (round chaining, the settle computation, lane coverage) is entirely CLI-owned; this skill is a thin driver. Do not reimplement settle logic or count rounds yourself — read what the CLI reports.
This is NOT the external-bot triage skill. /review-reply handles bot comments on a PR; do NOT invoke external review bots (CodeRabbit, Gemini Code Assist, Greptile) from here. This loop settles local findings first.
The loop
- Run the review.
totem reviewruns the repo's configured lanes. Do NOT pass--modelunless the user explicitly asked for a one-lane run — an explicit--modelselects a single-lane invocation and never joins the configured fan. Ifreview.lanesis not configured,totem reviewruns the legacy single-lane path and emits NO verdict artifact orlocal-lane:line — this loop's contract requires the verdict artifact, so configurereview.lanesfirst (a single entry suffices). - Read the reported outcome. The CLI reports the findings, the lane coverage (completed / attempted), the settled state, and the round number. Take them as reported — do not derive
settledyourself. - If not settled: apply fixes, then re-run. Fix the actionable findings — WARN and CRITICAL are actionable; INFO is cosmetic and can be skipped. Then re-run
totem review; the CLI chains the next round automatically from the prior verdict. An explicit--continues <verdict-hash>override exists for the rare case where the CLI reports a lineage fork you know is wrong (e.g. a rebase it mis-linked) — otherwise let it chain on its own. - Repeat until settled — or stop honestly. Loop until the CLI reports the round settled. Stop and report if the CLI's max-rounds advisory fires, or a finding is disputed. Never loop forever, and never silently override a disputed finding — a dispute goes to the human.
Honesty rules
- Never use
--overridewithout an explicit human go. It is trap-ledgered. - A degraded round is never settled. If completed < attempted (a lane failed), the round did not settle — say so; a dropped lane is not a pass.
- Report the outcome faithfully — the findings, the counts, and the settled state exactly as the CLI reports them.
At settle: hold the covariate line locally (never post a PR comment)
review-loop NEVER creates or posts a PR comment. The local loop runs BEFORE any external bot pass, and the round-disposition comment is ONE consolidated comment owned by the operator-invoked /review-reply workflow. At settle the CLI already prints the covariate line — hold and report it locally, in exactly this format:
<!-- covariate line format v1.2 — do not alter without a spec amendment (v1.1 added the additive admission form; v1.2 appends the leg field to both shapes and adds the `local-lane: none` head for a deposit-only lineage: mmnto-ai/totem#2698 design § Implementation Design, the .totem/specs/2473.md v1.2 clause) -->local-lane: <verdictHash8> round=<n> settled=<true|false> lanes=<completed>/<attempted> leg: <sha8> blocking=<n> material=<n> folded=<n>
local-lane: not-applicable (<reason>) recorded=<recordHash8> at=<createdAt> leg: <sha8> blocking=<n> material=<n> folded=<n>
local-lane: none leg: <sha8> blocking=<n> material=<n> folded=<n><verdictHash8> is the first 8 hex characters of the verdict artifact hash the CLI reports. The second shape is the ADMISSION form (format v1.1, mmnto-ai/totem#2473): rendered when the current diff resolves to a deterministic not-applicable admission — <recordHash8> addresses the admission record in .totem/artifacts/admissions/, and it is discriminated on the literal second token not-applicable. The third shape is the DEPOSIT-ONLY head: rendered when no verdict and no admission record exists for the lineage but a leg deposit resolves for HEAD, so a diff is never presented with no evidence line at all. leg: none replaces the field on the FIRST TWO shapes when no deposit resolves for HEAD; the third shape never carries it, because a deposit resolving is the only reason that shape renders. Consumers discriminate on the second token (<hash8> · not-applicable · none); <sha8> is the first 8 hex of the deposit's diffSha; a folded finding counts in both its severity bucket and folded. This line is a versioned contract consumed by a measurement pilot — do not change any shape without a spec amendment. The CLI renders every shape from its canonical artifacts via single core-owned renderers, so the line is re-derivable and never hand-authored — on demand, the read-only totem review --covariate (zero-LLM) resolves the current state and prints the verdict's line (admitted diff), the admission record's line (deterministic skip), or the deposit-only head (neither artifact exists for the lineage, but a leg read HEAD). Inclusion of any pending local-lane: line in the single consolidated round-disposition comment belongs to /review-reply (which obtains it by running totem review --covariate), not to this loop — never post it to GitHub yourself.
<!-- totem:skill-end -->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.

