stage-cli: Skill for Claude Code

.agents/skills/quality-review/SKILL.md

quality-review is a skill for Claude Code, Codex from ReviewStage/stage-cli. It costs 25 tokens per session (1,150 once invoked), scanned A, original, MIT.

A code-review workflow that checks changes against the implementation-quality rules in the nearest AGENTS.md file, a repository instruction file for coding agents. It assigns each rule a separate review and then removes duplicate or unsupported findings.

In plain words
What is it for?
Use it to review a set of code changes, read the applicable quality criteria, check every criterion independently, and produce a cleaned summary of findings.
Why use it?
It turns a broad quality review into checks tied to the project's actual rules. This helps avoid overlooking a requirement or reporting the same problem several times.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is ReviewStage/stage-cli's own configuration. It tells Claude Code and Codex how to work on stage-cli itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything stage-cli configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ReviewStage/stage-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ReviewStage/stage-cli/main/.agents/skills/quality-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ReviewStage/stage-cli

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for quality-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/reviewstage/stage-cli/quality-review/github.svg)](https://agentmods.dev/skills/reviewstage/stage-cli/quality-review)
Your own site
<a href="https://agentmods.dev/skills/reviewstage/stage-cli/quality-review"><img src="https://agentmods.dev/badge/skills/reviewstage/stage-cli/quality-review/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.

agentmods 80×15 button for quality-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/reviewstage/stage-cli/quality-review"><img src="https://agentmods.dev/badge/skills/reviewstage/stage-cli/quality-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,150 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.01150
Opus 5.5 $0.00010 $0.00460
Sonnet 5.5 $0.00005 $0.00230
Haiku 4.5 $0.00003 $0.00115

Measured 1mo ago against content hash f65bfe7355cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

quality-review 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 1mo ago.

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.

.agents/skills/quality-review/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quality Review

Overview

Dispatches one parallel Sonnet agent per bullet point in the ## Implementation Quality section of the nearest AGENTS.md. Each agent independently discovers what changed and checks the codebase against exactly one criterion. A triage pass then removes false positives, duplicates, and contradictions before the final report.

Workflow

1. PARSE    → Extract each bullet point from ## Implementation Quality in AGENTS.md
2. DISPATCH → One Task agent per criterion (all in parallel, single message)
3. TRIAGE   → Review all raw findings: drop false positives, duplicates, and contradictions
4. REPORT   → Compile cleaned findings into summary table

Step 1: Parse Criteria from AGENTS.md

Read the project's AGENTS.md and extract every bullet point under ## Implementation Quality. Stop at the next ## heading — do not include bullets from any other section. Each - line becomes one criterion.

Do not hardcode criteria — always read from the current project's AGENTS.md so the skill stays in sync with the project's actual standards.

Step 2: Dispatch Parallel Agents

CRITICAL: All agents must be launched in a SINGLE message with multiple Task tool calls. Do not loop sequentially.

Use subagent_type: "Explore" and model: "sonnet" on every Task call.

Agent prompt template for each criterion (set model: "sonnet" on every Task call):

You are a focused code reviewer responsible for checking ONE specific quality criterion.

Criterion:
{criterion_text}

Your job:
1. Discover what changed — start with `git diff origin/main...HEAD` or `git diff main...HEAD`.
2. Feel free to explore the broader codebase or search the web for anything — do as much research as needed to make a confident judgment.
3. Check whether the changes comply with your assigned criterion.
4. Report ALL violations you find — do not stop at the first one.

Output format (exactly this structure, nothing else):
**{criterion_short_name}**: PASS | WARN | FAIL
- `file:line` — description of violation  (repeat for every violation found)
(omit bullet lines entirely if PASS)

Read the full file on GitHub · 106 lines

Changes

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.

  1. 1mo ago First seen · 106 lines · 25 tokens per session scan A f65bfe7355cc

Subscribe to this mod's changes

quality-review is a skill published in the GitHub repository ReviewStage/stage-cli (274 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 1,150 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

autoreview

Structured code review through the shared OpenClaw agent-skills installation.

openclaw/clawhub · 17 tokens

omh-code-review

This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).

rlaope/oh-my-hermes · 48 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens

explore-unknowns

Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…

dzhng/skills · 162 tokens

asplos-writing-style

Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…

brycewang-stanford/Awesome-Journal-Skills · 65 tokens

re0-merge

Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…

LilMGenius/paperthin · 70 tokens