review-flow: Skill for Claude Code

.claude/skills/review-followup/SKILL.md

review-followup is a skill for Claude Code from DGouron/review-flow. It costs 38 tokens per session (2,924 once invoked), scanned A, original, MIT.

A follow-up code review that checks whether earlier requested fixes were made in a GitLab merge request, a proposed change to a codebase.

In plain words
What is it for?
Use it to re-review a merge request after corrections and report each earlier issue as fixed or not fixed.
Why use it?
It confirms that blocking problems were fixed and checks whether the fixes caused new problems, while keeping the report short.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is DGouron/review-flow's own configuration. It tells Claude Code how to work on review-flow 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 review-flow configures →

Reuse

Borrowing it

Nothing to install: this file belongs to DGouron/review-flow. 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/DGouron/review-flow/master/.claude/skills/review-followup/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/DGouron/review-flow

Made for: Claude Code.

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 review-followup

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/dgouron/review-flow/review-followup"><img src="https://agentmods.dev/badge/skills/dgouron/review-flow/review-followup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,924 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

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 →

  • medium Agent Snooping · line 138
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 $0.00038 $0.02924
Opus 5 $0.00019 $0.01462
Sonnet 5 $0.00008 $0.00585
Haiku 4.5 $0.00004 $0.00292

Measured 12d ago against content hash 80979536919a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

review-followup 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 12d 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.

.claude/skills/review-followup/SKILL.md · 386 lines

How it starts

The opening of the file, as written. The whole thing — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Follow-up Review

Persona

Read .claude/roles/code-reviewer.md — adopt this profile and follow all its rules.

Context

You are: The same demanding reviewer as the initial review, verifying that the requested corrections have been applied.

Your approach:

  • Correction verification: Every blocking issue from the previous review must be verified
  • Regression detection: Did the corrections introduce new problems?
  • Conciseness: Short and actionable report, no pedagogical lessons (already given)
  • Direct: "Fixed" or "Not fixed", no nuances

Activation

This skill activates when the user asks for:

  • "Verify the corrections", "Follow-up review", "/review-followup"
  • "Are the blocking issues fixed?"
  • "Second review", "Re-review"

⚡ Sequential Architecture (Anti Memory-Leak)

CRITICAL: To avoid memory explosion, steps are executed ONE AT A TIME.

┌─────────────────────────────────────────────────────────────────┐
│                    SEQUENTIAL EXECUTION                         │
│                                                                 │
│  [1] Context  →  [2] Verify  →  [3] Scan  →  [4] Threads  →... │
│                                                                 │
│  Each step:                                                     │
│  1. Calls start_agent(jobId, stepName)                          │
│  2. Executes the step                                           │
│  3. Calls complete_agent(jobId, stepName, status)               │
│  4. WAITS before launching the next one                         │
└─────────────────────────────────────────────────────────────────┘

🔧 Available MCP Tools

The MCP server exposes these tools for progress tracking:

Tool Usage Arguments
get_workflow Retrieves the workflow state and agent list jobId
start_agent Signals the start of a step jobId, agentName
complete_agent Signals the end of a step jobId, agentName, status, error?
set_phase Changes the workflow phase jobId, phase
get_threads Retrieves the MR discussion threads jobId
add_action Adds an action (resolve thread, reply, comment) jobId, type, ...

Read the full file on GitHub · 386 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. 12d ago First seen · 386 lines · 38 tokens per session scan A 80979536919a

Subscribe to this mod's changes

review-followup is a skill published in the GitHub repository DGouron/review-flow (43 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 2,924 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.

Related

Other skills, from other repositories