Borrowing it
Nothing to install: this file belongs to greenmtnsun/GitEasy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/greenmtnsun/GitEasy/main/.claude/skills/review-loop/SKILL.mdgit clone --depth 1 https://github.com/greenmtnsun/GitEasyWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/greenmtnsun/giteasy/review-loop)<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/review-loop"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/review-loop/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/review-loop"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/review-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00170 | $0.02706 |
| Opus 5.5 | $0.00068 | $0.01082 |
| Sonnet 5.5 | $0.00034 | $0.00541 |
| Haiku 4.5 | $0.00017 | $0.00271 |
Grade A, and why
review-loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review loop
A review loop is one review that repeats until no finding is open. A fresh reviewer finds problems, the builder fixes them or proposes a waiver, tests run again, and a new reviewer checks the result. Keith adopted it for the official delivery process on 2026-11-14 and amended it on 2026-11-15.
Where the rules live
There is one copy of the rules. This skill points at it and doesn't restate the numbers.
| What | Where |
|---|---|
| The rules (spec 1.2.x) | C:\Users\keith\.claude\skills\delivery-pipeline\review-loops.json |
| The control flow | C:\Users\keith\.claude\skills\delivery-pipeline\uml\01-activity-review-phase.puml and 02-activity-review-loop.puml |
| The running code | C:\Users\keith\.claude\workflows\delivery-pipeline.js (reviewPhase, reviewLoop, haltForKeith) |
| The tests | C:\Users\keith\.claude\skills\delivery-pipeline\tests\run-scenarios.js |
| How to use it, for people | guide\review-loops-guide.html and guide\review-loops-guide.pdf beside this file |
Read review-loops.json before running a loop by hand. It's short, and it holds the round caps, the
size rule, the waiver limits and the stop rules.
The loop
- Size the work first, by
loop.sizein the spec. A small item gets one reviewer per round who applies both the code and the security checks, and a lower round cap. Anything bigger gets separate code and security loops and the normal cap. Keith set this on 2026-11-15 after a loop on a 40-line function ran 96 minutes with two reviewers a round. - A fresh reviewer agent reviews the work. It never built or repaired it. From round 2 it reports on every earlier finding by id before it looks for new ones.
- No open findings: the loop is clean.
- Any of these stops the loop and goes to Keith:
- a diagram,
Steps:or code mismatch (CLAUDE.md section 5); - a finding still open after 2 repair rounds (CLAUDE.md section 18);
- a medium or worse finding still open at the round cap;
- a builder escalation, or a waiver proposed for a critical or high finding. This stop comes straight after the repair round, so that round's repairs aren't re-tested or reviewed. Keith kept it that way on 2026-11-15, because a resume with his ruling reruns that round anyway.
- a diagram,
- At the round cap with only low findings open, the loop ends as carried: those findings go to the ledger as open items for Keith, and the work goes on.
- Otherwise the builder repairs each finding or proposes a waiver with a reason. Tests and static analysis run again. Every other review in the same phase looks again at the files that changed.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 180 lines · 170 tokens per session scan A 0afcc381557d
review-loop is a skill published in the GitHub repository greenmtnsun/GitEasy (1 stars, last pushed yesterday), licensed MPL-2.0. It adds 170 tokens to every session and 2,706 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-18.
review-loop compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| review-loopgreenmtnsun/GitEasy | Skill | 1 | yesterday | MPL-2.0 | A | 170 | Claude Code |
| autoreviewopenclaw/clawhub | Skill | 9.6k | today | MIT | A | 17 | Claude Code, Codex |
| agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills | Skill | 2.2k | 6d ago | MIT | A | 115 | Claude Code, Codex |
| revdiff-planumputun/revdiff | Skill | 961 | today | MIT | A | 84 | Claude Code |
| re0-mergeLilMGenius/paperthin | Skill | 1.5k | 3d ago | MIT | A | 51 | Claude Code, Codex |
| explore-unknownsdzhng/skills | Skill | 1.5k | 5d ago | MIT | A | 162 | Claude Code, Codex |
| asplos-writing-stylebrycewang-stanford/Awesome-Journal-Skills | Skill | 1.4k | 1mo ago | MIT | A | 65 | Claude Code |