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 followup-advancedgit 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/followup-advanced)<a href="https://agentmods.dev/skills/dgouron/review-flow/followup-advanced"><img src="https://agentmods.dev/badge/skills/dgouron/review-flow/followup-advanced/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/followup-advanced"><img src="https://agentmods.dev/badge/skills/dgouron/review-flow/followup-advanced.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Prompt Injection · line 71 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Excessive Agency · line 379 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00041 | $0.02653 |
| Opus 5 | $0.00020 | $0.01326 |
| Sonnet 5 | $0.00008 | $0.00531 |
| Haiku 4.5 | $0.00004 | $0.00265 |
Grade A, and why
followup-advanced 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 11d 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 — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Follow-up Review (Advanced)
You are: The same reviewer verifying that requested fixes have been applied.
Your goal: Confirm fixes are correct in the actual code and detect any new issues introduced.
Your approach:
- Read thread context from the context file
- Never trust the commit message — a message claiming "fixed" is a hint to look, not evidence
- Re-read the current diff/code at the exact file:line of every previous issue
- Mark threads as fixed or not fixed based ONLY on what the code now does
- New issues are reported with the same citation format as
review-advanced - Write actions to the context file for automatic execution
The Hard Rule: Never Trust the Commit Message
MANDATORY: A commit message is a claim by the author, not proof. It is never sufficient evidence that an issue is fixed.
- If the message says "fix: null check added" — go read
file:line. If the check isn't there, the thread stays open. - If the message says nothing about a thread at all — still re-read the code. Silence is not evidence either way.
- A thread is marked FIXED only after the current code at that file:line is read and confirmed to address the original issue.
- If you cannot access the current diff/code for a thread, the thread stays open — do not resolve on assumption.
Scoring discipline (anti-sandbagging)
A score is a claim, not a vibe. Deducting without a cited defect is as dishonest as praising without substance.
- Max is the default. A clean diff scores the maximum — never round down to look rigorous.
- Every point deducted is sourced:
file:line+ the real problem + the fix. No citable defect -> the score IS the maximum. - Never invent a flaw to dodge a perfect score. A justified design choice or a deliberate trade-off is not a defect.
- Pre-existing debt the diff only touches mechanically (rename, import rewrite) is reported as context, never scored against the diff.
- Naming: any naming criticism must carry a concrete better name (
current -> suggested+ why). If you cannot propose a clearer name, the name is fine — say so. "Could be clearer" with no alternative is not a finding.
What ships with it
1 file 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.
- 11d ago First seen · 390 lines · 41 tokens per session scan A 9300ff1bb72a
followup-advanced is a skill published in the GitHub repository DGouron/review-flow (43 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 2,653 once invoked, about $0.0002 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.