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 nimadorostkar/Claude-Skills-collection --skill skill-reviewgit clone --depth 1 https://github.com/nimadorostkar/Claude-Skills-collectionWrote 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/nimadorostkar/claude-skills-collection/skill-review)<a href="https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/skill-review"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/skill-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/nimadorostkar/claude-skills-collection/skill-review"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/skill-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00035 | $0.01193 |
| Opus 5 | $0.00017 | $0.00596 |
| Sonnet 5 | $0.00007 | $0.00239 |
| Haiku 4.5 | $0.00003 | $0.00119 |
Grade A, and why
skill-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 13d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Review
Purpose
Assess whether a skill earns its place. A skill costs context and attention every time it loads; it must return more than it costs.
When to Use
- Reviewing a skill before publishing it.
- A skill that triggers unreliably.
- Auditing a skill library for redundancy and dead weight.
- Deciding whether two skills should be merged or split.
Capabilities
- Triggering evaluation: does it fire when it should, and stay silent when it should not?
- Content quality: is the guidance specific, correct, and actionable?
- Redundancy check: does it tell the model something it does not already do?
- Overlap detection across a library.
Inputs
- The skill, and the library it sits in.
- Real user phrasings for the task it addresses.
- The model's behavior on that task without the skill.
Outputs
A verdict with specifics:
- Keep — Triggers correctly, changes behavior for the better.
- Revise — Named defects: description, content, or scope.
- Merge or delete — It duplicates another skill, or adds nothing.
Workflow
- Test the triggering first — Ten phrasings that should trigger it, and five that should not. This is the fastest way to find that a skill is unusable, and it is the most common defect.
- Run the task without the skill — Establish the baseline. If the model already handles the task well, the skill is not needed.
- Run it with the skill — Compare. The difference is the skill's entire value. If there is no difference, delete it.
- Read the content critically — Is it specific enough to act on? Are the constraints real rules or vague preferences? Do the examples show the actual output shape?
- Check for overlap — Two skills that both trigger on the same request will both load, doubling the cost and possibly contradicting each other.
- Check the accuracy — Outdated practices in a skill are worse than no skill, because the model will follow them confidently.
Best Practices
- The behavioral difference is the only measure that matters. A beautifully written skill that does not change the output is decoration.
- A skill that triggers on 30% of the requests it should is broken, however good its content is. Fix the description first — content quality is irrelevant if the skill never loads.
- Look for guidance that was true two years ago and is not now. Skills rot, and a confidently stated obsolete practice is a liability.
- Two skills with overlapping descriptions will both load. Either the boundary must be sharpened in both descriptions, or they should be one skill.
- Prose that describes a domain rather than instructing an action is filler. Cut it.
- A skill with no constraints ("prefer clean code") is not a skill. It is a sentiment.
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.
- 13d ago First seen · 115 lines · 35 tokens per session scan A 37079a5b16ac
skill-review is a skill published in the GitHub repository nimadorostkar/Claude-Skills-collection (26 stars, last pushed 25d ago), licensed MIT. It adds 35 tokens to every session and 1,193 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 2026-08-30.
Other skills, from other repositories
offensive-crypto-attacks
Systematic methodology for identifying and exploiting cryptographic implementation weaknesses in real-world applications. Covers padding oracle attacks against CBC-mode ciphers with PKCS7 padding (Vaudenay's original attack through modern padbuster automation), ECB mode exploitation including block cut-and-paste and…
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
offensive-parameter-pollution
HTTP parameter pollution (HPP) checklist: duplicate parameter injection, backend vs frontend parsing differences, WAF bypass via HPP, server-side vs client-side HPP, and practical exploitation patterns. Use when testing web applications for parameter handling flaws.
offensive-wifi
Wireless / 802.11 attack methodology for red team engagements and wireless security assessments. Covers monitor-mode setup, WPA/WPA2-PSK handshake capture and PMKID attacks, WPA3 SAE downgrade and Dragonblood, WPA-Enterprise (EAP) attacks (MSCHAPv2 cracking, EAP-TLS cert theft, evil-twin RADIUS), Karma / Known Beacons…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
seo
Optimize for search engine visibility and ranking. Use when asked to "improve SEO", "optimize for search", "fix meta tags", "add structured data", "sitemap optimization", or "search engine optimization".