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 maxence2997/mx-harness --skill mx-review-triagegit clone --depth 1 https://github.com/maxence2997/mx-harnessWrote 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/maxence2997/mx-harness/mx-review-triage)<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.
<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>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 | $0.00086 | $0.01771 |
| Opus 5 | $0.00043 | $0.00886 |
| Sonnet 5 | $0.00017 | $0.00354 |
| Haiku 4.5 | $0.00009 | $0.00177 |
Grade A, and why
mx-review-triage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mx-review-triage
Trigger
/mx-review-triage ← auto-detect source
/mx-review-triage --source review ← local mx-team-review report
/mx-review-triage --source pr <id|url> ← GitHub / GitLab PR comments
Orchestrated mode
Step 5 pauses for user approval of the triage table. When invoked from an orchestrator that declares auto-proceed for its triage gate (e.g. mx-flow GATE 3), skip that pause: show the full triage table, treat all "Fix now" items as approved, and execute them immediately. "Track" and "Skip" buckets behave as written. When invoked directly by the user, the pause applies as written.
Hard gate: with --source pr, this skill does not finish until zero
unresponded comments remain (Step 7).
Step 1 — Determine source
If --source review
Find the most recent review report:
- Resolve repo root:
REPO_ROOT=$(git rev-parse --show-toplevel). If running inside a linked worktree, also resolve the main repository root (.mx/lives there):MAIN_ROOT=$(cd "$(dirname "$(git rev-parse --git-common-dir)")" && pwd)(in a normal checkout MAIN_ROOT resolves to the same directory as REPO_ROOT) - Check
.mx/*/tmp/review-*.mdunder$REPO_ROOTand$MAIN_ROOT(project-local active feature path) - 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 apito fetch review comments and issue comments - GitLab:
glab apito 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.
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.
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.
- yesterday Changed · +22 lines e4ac85ef5cd3
- 9d ago First seen · 158 lines · 86 tokens per session scan A a6ea6d8bcc0b
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.
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.
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…
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…
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…
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…
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".