review-skill

review-skill is a skill for Claude Code, Codex from runxhq/runx. It costs 57 tokens per session (803 once invoked), scanned A, original, Apache-2.0.

A review tool for examining one Runx skill package and assessing what it can do, how trustworthy it is, and whether it is ready for operators. It uses bounded evidence and can run safe read-only or planning tests.

In plain words
What is it for?
Use it to inspect a skill's capabilities, test its safe paths, check refusal and authority boundaries, and assess its readiness.
Why use it?
It separates observed test results from documentation and unverified claims. This helps you decide whether to adopt, improve, reject, install, or publish a skill without changing the package.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to inspect a skill's capabilities, test its safe paths, check refusal and authority boundaries, and assess its readiness.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/runxhq/runx/review-skill
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 runxhq/runx --skill review-skill
Clone the repo
git clone --depth 1 https://github.com/runxhq/runx

Made for: Claude Code, Codex.

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-skill

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/runxhq/runx/review-skill"><img src="https://agentmods.dev/badge/skills/runxhq/runx/review-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 803 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 pass 7 Sept 2026
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 $0.00057 $0.00803
Opus 5 $0.00028 $0.00402
Sonnet 5 $0.00011 $0.00161
Haiku 4.5 $0.00006 $0.00080

Measured 6d ago against content hash 0bb55d42aad9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review-skill 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 6d 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.

skills/review-skill/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Skill

Evaluate one skill from bounded evidence. The default runner passes a local package to native runx.skill.validate, which parses and inspects the exact package, runs read-only or planning harnesses with isolated receipts and no operator credentials, and forwards that evidence to the focused assessment runner. Execute-capable targets are inspected but never run automatically.

This skill does not mutate the package, publish a report, install a package, or manufacture missing evidence. Use assess directly when a caller already has a bounded evidence pack.

Procedure

  1. Resolve a workspace- or owning-skill-relative package path and capture its native capability and readiness envelope. Registry or marketplace material must first be installed or supplied as a bounded evidence pack; this skill does not fetch it implicitly.
  2. Run the native harness only when catalog execution is read or plan.
  3. Compare the documented capability with the inspected runner and catalog metadata in the evidence pack.
  4. Separate native harness results, provider readback, supplied assertions, and unverified claims.
  5. Check the happy path, refusal or stop path, authority boundary, artifact or effect, provenance, and recovery posture appropriate to the skill type.
  6. Return needs_more_evidence when the evidence cannot support a trust decision. Never upgrade a parse result or prose claim into execution proof.
  7. Recommend adopt, adopt_with_caveats, improve, or reject, naming the evidence and blocking gaps behind the decision.

Stop conditions

  • Refuse evidence containing secrets, raw credentials, private customer data, private inbox content, or provider dumps.
  • Do not recommend provider readiness without provider readback.
  • Do not recommend publication from private previews, placeholder hosts, dead links, or unrelated parent domains.
  • Return needs_more_evidence when no native inspection, harness, receipt, or equivalent bounded source evidence is supplied.
  • Reject capabilities that cannot be bounded, audited, or assigned a truthful terminal state.

Read the full file on GitHub · 78 lines

Files

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.

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. 6d ago First seen · 78 lines · 57 tokens per session scan A 0bb55d42aad9

Subscribe to this mod's changes

review-skill is a skill published in the GitHub repository runxhq/runx (84 stars, last pushed today), licensed Apache-2.0. It adds 57 tokens to every session and 803 once invoked, about $0.0003 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 2026-09-03.