Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add DGouron/review-flow --skill review-bootstrapgit clone --depth 1 https://github.com/DGouron/review-flowWrote 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/dgouron/review-flow/review-bootstrap)<a href="https://agentmods.dev/skills/dgouron/review-flow/review-bootstrap"><img src="https://agentmods.dev/badge/skills/dgouron/review-flow/review-bootstrap/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/dgouron/review-flow/review-bootstrap"><img src="https://agentmods.dev/badge/skills/dgouron/review-flow/review-bootstrap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 16 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
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 | $0.00024 | $0.00850 |
| Opus 5 | $0.00012 | $0.00425 |
| Sonnet 5 | $0.00005 | $0.00170 |
| Haiku 4.5 | $0.00002 | $0.00085 |
Grade A, and why
review-bootstrap 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Bootstrap - Context Communication Protocol
CRITICAL INSTRUCTIONS - MANDATORY EXECUTION
THIS IS NOT OPTIONAL. YOU MUST FOLLOW THESE INSTRUCTIONS NO MATTER WHAT.
Step 1: Locate and Read the Context File
At the START of your review, you MUST:
- Find the context file in
.claude/reviews/logs/directory - The file is named
{platform}-{project}-{mrNumber}.json - READ this file to get:
threads: List of existing threads with their IDsagentInstructions: Instructions you MUST follow
Step 2: Understand the Thread Structure
Each thread in the threads array has:
{
"id": "abc123def...", // EXACT ID to use for actions
"file": "path/to/file.ts",
"line": 42,
"status": "open", // "open" or "resolved"
"body": "Original comment"
}
Step 3: After Your Analysis - UPDATE THE FILE
CRITICAL - DO NOT SKIP THIS STEP
After completing your review analysis, you MUST update the context file:
-
For EACH thread you determine is FIXED/CORRECTED:
- Add a
THREAD_RESOLVEaction to theactionsarray - Use the EXACT
idfrom the thread
- Add a
-
Use the Write tool to update the file
Action Format
{
"actions": [
{
"type": "THREAD_RESOLVE",
"threadId": "abc123def..."
},
{
"type": "THREAD_REPLY",
"threadId": "xyz789ghi...",
"message": "Verified: the fix correctly addresses the issue."
},
{
"type": "POST_INLINE_COMMENT",
"filePath": "src/path/to/file.ts",
"line": 42,
"body": "Comment on this line of the diff"
},
{
"type": "POST_COMMENT",
"body": "Global comment on the MR/PR"
}
]
}
Example Workflow
1. Read context file
2. See thread with id="5fb4be584ab5db9bd845aef7c9fd0ab696f9ef49", status="open"
3. Analyze the code - determine the issue is FIXED
4. Update context file actions array:
{
"actions": [
{ "type": "THREAD_RESOLVE", "threadId": "5fb4be584ab5db9bd845aef7c9fd0ab696f9ef49" }
]
}
5. Write the updated JSON to the same file path
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.
- 9d ago First seen · 120 lines · 24 tokens per session scan A 745db2cf43ad
review-bootstrap is a skill published in the GitHub repository DGouron/review-flow (43 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 850 once invoked, about $0.0001 per session on Opus 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.
Other skills, from other repositories
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…
new-skill
Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.
address-review
Read PR review comments from GitHub, evaluate, address, and reply.