Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/oaustegard/claude-skillsnpx agentmods add skills/oaustegard/claude-skills/optimizing-skillsWrote 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/oaustegard/claude-skills/optimizing-skills)<a href="https://agentmods.dev/skills/oaustegard/claude-skills/optimizing-skills"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/optimizing-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/oaustegard/claude-skills/optimizing-skills"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/optimizing-skills.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 | $0.00104 | $0.02115 |
| Opus 5 | $0.00052 | $0.01058 |
| Sonnet 5 | $0.00021 | $0.00423 |
| Haiku 4.5 | $0.00010 | $0.00212 |
Grade A, and why
optimizing-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 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.
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimizing Skills
Treat the skill document as the parameter under optimization: change it only when the change demonstrably beats the version you already ship. This is the discipline distilled from SkillOpt (microsoft/SkillOpt, arXiv:2605.23904) — its training apparatus dropped, its reproducibility discipline kept. The point is to stop editing skills on intuition and start editing them on evidence.
Core principle
A skill edit is only worth shipping if it strictly improves measured behavior on a held-out check. Most edits that feel like improvements don't move the needle, and some quietly regress. The gate below is what separates a real improvement from a confident guess.
The gate — run it every revision
- Assemble a held-out check set. 3–8 representative tasks/prompts the skill should handle well, and it must include the failure(s) that prompted this revision. Keep the set fixed across the revision so before/after scores are comparable.
- Hold two versions.
best= what you currently ship (never let it silently degrade).candidate=best+ your proposed edits. - Score both on the check set. "Run" here = dispatch each check task to the
Agent tool (
subagent_type=general-purpose) with the skill version in context, or evaluate by hand for small sets. Give the scoring agent the skill version and the task, and nothing else. Never hand it the ledger, your revision notes, or the diagnosis that motivated the edit: it will solve the task from those instead of from the skill, and the score stops measuring the skill. WikiSkill (arXiv:2608.27454) ablated exactly this and lost 2.8 points of final quality, 7.8 on their hardest split, by letting the worker read the improver's knowledge store. Score per criterion, not one collapsed pass/fail. When a task carries several criteria, the criterion that decides accept/reject is the failure that prompted this revision; the others are regression guards that must not get worse. Collapsing criteria masks the win: in the down-skilling-v1.2.0 retro, the edit drove architectural hallucination 60%→0% while an unrelated length criterion stayed 0/5 in both arms — a single combined pass/fail scored that as a 0–0 tie and would have rejected a large, real improvement. - Accept only if
candidatestrictly beatsbeston the triggering-failure criterion, with no regression guard worse. Ties → reject, keepbest. An edit that doesn't move the needle does not ship.
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.
- 6d ago Changed · +42 lines 70790889fc81
- 9d ago First seen · 130 lines · 104 tokens per session scan A ec1bec8b6842
optimizing-skills is a skill published in the GitHub repository oaustegard/claude-skills (148 stars, last pushed yesterday), licensed MIT. It adds 104 tokens to every session and 2,115 once invoked, about $0.0005 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
superdesign
Design or redesign frontend UI, presentations, and graphics on the Superdesign canvas with a choice of leading AI models. Use whenever the user wants to design a page, feature, flow, slide deck, or brand-new product; improve or reproduce existing UI; compare design results across top models; explore visual variants…
Linear
Managing Linear issues, projects, and teams. Use when working with Linear tasks, creating issues, updating status, querying projects, or managing team workflows.
chanlun-engine-skill
A Chinese-language stock-analysis skill based on Chan theory, a method for interpreting price-chart structures such as turning points and trading ranges.
youtube-summary
Summarize a YouTube video into structured notes — TL;DR, key takeaways, chapter-by-chapter breakdown, and reference links. Use when the user shares a YouTube URL (or invokes /youtube-summary ) and wants a summary, takeaways, transcript notes, or a write-up of a talk, lecture, or tutorial. Fetches the transcript and…
plangate
Use for any non-trivial task with 2+ open decisions/tradeoffs OR multiple implementation steps — instead of deliberating one question at a time in chat, write a structured plan to a file and let the user review it inline in vim with > Q: / > A: blockquote markers, then revise until agreed before touching any code.…
coinmarketcap
Expert assistant for CoinMarketCap Pro API — price quotes, listings, historical OHLCV, market metrics, Fear & Greed Index, CMC100/CMC20 indices, exchange data, DEX data, airdrops, trending, community sentiment. Covers 10+ endpoint categories across REST + MCP + x402 pay-per-call modes. Use when the user wants: current…