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 tomzx/agents --skill review-skillsgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/review-skills)<a href="https://agentmods.dev/skills/tomzx/agents/review-skills"><img src="https://agentmods.dev/badge/skills/tomzx/agents/review-skills/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/tomzx/agents/review-skills"><img src="https://agentmods.dev/badge/skills/tomzx/agents/review-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Memory Poisoning · line 169 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00046 | $0.03431 |
| Opus 5 | $0.00023 | $0.01716 |
| Sonnet 5 | $0.00009 | $0.00686 |
| Haiku 4.5 | $0.00005 | $0.00343 |
Grade A, and why
review-skills 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 9d 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 — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Skills
Audits a directory of skills for structural and semantic issues across seven categories: duplicates, broken references, circular dependencies, orphaned skills, composability, re-run safety, and skill gaps. Produces a prioritized report with concrete remediation steps.
Prerequisites
- A directory containing skill subdirectories, each with a
SKILL.mdfile - If no directory is provided, infer the active skill directory from the current agent/harness configuration (see Step 1)
What Gets Checked
| Category | Description |
|---|---|
| Duplicates | Skills with overlapping or identical purpose, name, or description |
| Broken references | Cross-references to skills, files, or tools that do not exist |
| Circular dependencies | Chains of skill invocations that form a cycle |
| Orphaned skills | Skills never referenced or invoked by any other skill |
| Composability | Skills that cannot be composed because of conflicting interfaces, missing prerequisites, or incompatible tool constraints |
| Re-run safety | Skills that may behave incorrectly or destructively when invoked multiple times on the same inputs |
| Skill gaps | Common agent workflows that lack a corresponding skill |
Steps
1. Determine the skills directory
If $1 is provided, use it.
Otherwise, locate the active skill directory by checking in order:
.opencode/skills/in the current repository root~/.opencode/skills/.agents/skills/in the current repository root~/.agents/skills/
If none exist, report the error and stop.
Validate that the chosen directory contains at least one SKILL.md:
find "$SKILLS_DIR" -mindepth 2 -name "SKILL.md" -type f | head -1
2. Build the skill index
For every SKILL.md in the directory, extract:
- name from frontmatter
namefield - description from frontmatter
descriptionfield - allowed-tools from frontmatter (if present)
- argument-hint from frontmatter (if present)
- directory name (the folder containing the SKILL.md)
- section headers (all
##and###headings) - line count
- references to other skills (see extraction rules below)
- referenced by (populated by cross-referencing in step 3)
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.
- 9d ago First seen · 324 lines · 46 tokens per session scan A a531b70c41ef
review-skills is a skill published in the GitHub repository tomzx/agents (8 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 3,431 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…