mx-review-triage

mx-review-triage is a skill for Claude Code from maxence2997/mx-harness. It costs 86 tokens per session (1,771 once invoked), scanned A, original, MIT.

A review-feedback sorter that reads findings from local review reports or GitHub and GitLab pull-request comments, then groups them by whether to fix, track, or skip.

In plain words
What is it for?
Use it after a code review to assess each finding by severity, validity, and effort, request approval when needed, and carry out the approved fixes.
Why use it?
It helps separate valid, urgent issues from lower-priority or invalid feedback before merging code, so developers can focus on approved changes.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it after a code review to assess each finding by severity, validity, and effort, request approval when needed, and carry out the approved fixes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/maxence2997/mx-harness/mx-review-triage
Install

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.

Any agent
npx skills add maxence2997/mx-harness --skill mx-review-triage
Clone the repo
git clone --depth 1 https://github.com/maxence2997/mx-harness

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 mx-review-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/maxence2997/mx-harness/mx-review-triage/github.svg)](https://agentmods.dev/skills/maxence2997/mx-harness/mx-review-triage)
Your own site
<a href="https://agentmods.dev/skills/maxence2997/mx-harness/mx-review-triage"><img src="https://agentmods.dev/badge/skills/maxence2997/mx-harness/mx-review-triage/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 mx-review-triage

Your own site · 80×15
<a href="https://agentmods.dev/skills/maxence2997/mx-harness/mx-review-triage"><img src="https://agentmods.dev/badge/skills/maxence2997/mx-harness/mx-review-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,771 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.
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 $0.00086 $0.01771
Opus 5 $0.00043 $0.00886
Sonnet 5 $0.00017 $0.00354
Haiku 4.5 $0.00009 $0.00177

Measured yesterday against content hash e4ac85ef5cd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mx-review-triage 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 yesterday.

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.

mx-review-triage/SKILL.md · 180 lines

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.

mx-review-triage

Trigger

/mx-review-triage                       ← auto-detect source
/mx-review-triage --source review       ← local mx-team-review report
/mx-review-triage --source pr <id|url>  ← GitHub / GitLab PR comments

Orchestrated mode

Step 5 pauses for user approval of the triage table. When invoked from an orchestrator that declares auto-proceed for its triage gate (e.g. mx-flow GATE 3), skip that pause: show the full triage table, treat all "Fix now" items as approved, and execute them immediately. "Track" and "Skip" buckets behave as written. When invoked directly by the user, the pause applies as written.

Hard gate: with --source pr, this skill does not finish until zero unresponded comments remain (Step 7).


Step 1 — Determine source

If --source review

Find the most recent review report:

  1. Resolve repo root: REPO_ROOT=$(git rev-parse --show-toplevel). If running inside a linked worktree, also resolve the main repository root (.mx/ lives there): MAIN_ROOT=$(cd "$(dirname "$(git rev-parse --git-common-dir)")" && pwd) (in a normal checkout MAIN_ROOT resolves to the same directory as REPO_ROOT)
  2. Check .mx/*/tmp/review-*.md under $REPO_ROOT and $MAIN_ROOT (project-local active feature path)
  3. Fall back to /tmp/review-reports/ (Unix) or %TEMP%\review-reports\ (Windows)

Pick the file with the latest modification time across both locations. If no report exists in either location, report the error and stop.

If --source pr <id|url>

Detect the platform from the repo's remote URL:

  • GitHub: gh api to fetch review comments and issue comments
  • GitLab: glab api to fetch MR discussions and notes

Filter out:

  • Comments already replied to by the PR author
  • Bot-generated summary comments (e.g. Copilot review overview)
  • Individual line comments from bots MUST still be evaluated

If the platform CLI is absent or its call fails for any reason (not installed, not authenticated, network, 4xx/5xx), stop and report the exact error — never treat a failed fetch as "no comments"; Step 7's gate cannot pass on an unread PR. If the remote is neither GitHub nor GitLab, say so and ask the user for the comment source.

Read the full file on GitHub · 180 lines

Files

What ships with it

3 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.

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. yesterday Changed · +22 lines e4ac85ef5cd3
  2. 9d ago First seen · 158 lines · 86 tokens per session scan A a6ea6d8bcc0b

Subscribe to this mod's changes

mx-review-triage is a skill published in the GitHub repository maxence2997/mx-harness (5 stars, last pushed 2d ago), licensed MIT. It adds 86 tokens to every session and 1,771 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

cn-check

Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.

continuedev/continue · 49 tokens

resolve-pr-comments

Evaluate, fix, answer, and reply to GitHub pull request review comments and conversation comments. Handles both change requests (fix or skip) and reviewer questions (explain using reasoning recalled from past Claude Code transcripts). Use when the user asks to "resolve PR comments", "fix review comments", "address PR…

tobihagemann/turbo · 95 tokens

review-code

Review code for bugs, security vulnerabilities, API misuse, consistency issues, simplicity problems, or test coverage gaps by running internal reviews and a peer review in parallel and returning combined findings. Single-concern with a type argument, or full review with no argument. Use when the user asks to "review…

tobihagemann/turbo · 144 tokens

assess-technical-debt

Assess project-wide structural technical debt: complexity hotspots, deprecated API usage, duplication clusters, and architecture rot. Ranks findings by impact and refactor effort into a report at .turbo/technical-debt.md. Use when the user asks to "assess technical debt", "find technical debt", "review technical…

tobihagemann/turbo · 108 tokens

map-codebase

Deep architecture report that fans out parallel inspections across different aspects of the codebase (structure, tech stack, APIs, patterns, data flow, dependencies, testing) and synthesizes findings into a comprehensive document at .turbo/codebase-map.md and .turbo/codebase-map.html. Use when the user asks to "map…

tobihagemann/turbo · 106 tokens

peer-review

Run an independent peer review via Codex. Use when the user asks to "peer review", "peer review my code", "peer review my plan", "get a second opinion", or "independent review".

tobihagemann/turbo · 46 tokens