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-team-reviewgit 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-team-review)<a href="https://agentmods.dev/skills/maxence2997/mx-harness/mx-team-review"><img src="https://agentmods.dev/badge/skills/maxence2997/mx-harness/mx-team-review/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-team-review"><img src="https://agentmods.dev/badge/skills/maxence2997/mx-harness/mx-team-review.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 | $0.00075 | $0.03106 |
| Opus 5.5 | $0.00030 | $0.01242 |
| Sonnet 5.5 | $0.00015 | $0.00621 |
| Haiku 4.5 | $0.00007 | $0.00311 |
Grade A, and why
mx-team-review 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 29d 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 — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Orchestrator
Trigger
/mx-team-review [diff-spec]
/mx-team-review --repo <path>
Orchestrated mode
Step 6 (interactive review of the report) pauses for the user. When invoked from an orchestrator at all (mx-flow Phase 5b, or any orchestrator that declares auto-proceed for a gate), skip the pause: save and display the report, then return control — triage happens in the orchestrator's next step. When invoked directly by the user, Step 6 applies as written.
Step 1: Parse Arguments and Determine Mode
Parse the user's argument to determine the review mode:
| Invocation | Mode | Action |
|---|---|---|
/mx-team-review (no args) |
diff | git diff --cached (staged changes) |
/mx-team-review HEAD~3 |
diff | git diff HEAD~3..HEAD |
/mx-team-review main..HEAD |
diff | git diff main..HEAD |
/mx-team-review abc..def |
diff | git diff abc..def |
/mx-team-review --repo src/service/ |
repo | Read all code files in directory |
/mx-team-review --repo src/service/order.go |
repo | Read specific file(s) |
Argument parsing:
- If argument starts with
--repo→ repo mode. The path(s) follow. - Otherwise → diff mode. If no argument, default to
--cached.
Validation:
- Diff mode: run the git diff command. If output is empty, print
No changes to review.and stop. - Repo mode: check if path exists. If not, print error and stop.
Display: 📋 Reviewing: {description of what is being reviewed}
Step 1.5: Right-Size the Review
Size the job before spending anything on it. In diff mode, read the size off the diff Step 1 already ran. In repo mode, list the files under the target path now (Step 3 reuses the list).
- No source files (docs/config only —
.md,.txt,.json,.yaml,.yml,.toml,.xml): say so and run a single Future Maintainer pass (Step 4B, perspective 3 only — no Tech Lead synthesis). Do not dispatch reviewers. Files routed here count as explicitly targeted, so Step 3 reads them rather than applying its config skip-list. - Under ~30 changed lines in a single file (diff mode; in repo mode, a single file of comparable size): use Step 4B regardless of Agent-tool availability.
- Otherwise: continue with the full pipeline.
What ships with it
6 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.
- 29d ago Changed 5d70c4ea6f6a
- 1mo ago Changed · +55 lines · -3 tokens per session 816cfb667440
- 1mo ago First seen · 292 lines · 78 tokens per session scan A e566ed6c68fb
mx-team-review is a skill published in the GitHub repository maxence2997/mx-harness (5 stars, last pushed 29d ago), licensed MIT. It adds 75 tokens to every session and 3,106 once invoked, about $0.0003 per session on Opus 5.5. 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
code-refiner
Deep code simplification and refactoring preserving behavior across Python, Go, TypeScript, Rust. Targets complexity, anti-patterns, readability debt. Triggers on: "simplify this code", "refactor for clarity", "reduce complexity", "make this more readable", "tech debt cleanup", "too much nesting".
package-evaluator
Use when evaluating an Armory package, auditing agent or hook quality, checking package completion contracts, or reviewing the catalog across package types. Covers single-package and repository-wide audits. Not for LLM prompt optimization or ordinary PR code review.
codebase-advisor
Senior codebase advisor that audits a repository, vets findings, and writes self-contained implementation plans for other agents to execute. Triggers on: "write improvement plans", "create an implementation backlog", "audit and plan fixes", "turn findings into plans", "agent-executable plans", "reconcile plans"…
pr-review
Diff-based PR review across code quality, test coverage, silent failures, type design, and comment quality with severity-ranked findings. Triggers on: "review my PR", "review this code", "check my changes", "audit this PR", "code review". NOT for pre-landing gate, use pre-landing-review.
devils-advocate
Challenges AI-generated plans, code, and designs via pre-mortem, inversion, and Socratic questioning to surface blind spots and failure modes. Triggers on: "challenge this", "devils advocate", "stress test this plan", "poke holes in this", "what am I missing".
package-optimizer
Evaluate one existing package or bounded package family from recorded evaluator evidence and a capability profile, then propose retain, simplify, strengthen, retire, or inconclusive without editing. Use when optimizing a skill, agent, hook, rule, command, utility, or preset; evaluating whether package detail is…