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 agentmods add instructions/fastxyz/skill-optimizer/claude-mdgit clone --depth 1 https://github.com/fastxyz/skill-optimizerWrote 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/instructions/fastxyz/skill-optimizer/claude-md)<a href="https://agentmods.dev/instructions/fastxyz/skill-optimizer/claude-md"><img src="https://agentmods.dev/badge/instructions/fastxyz/skill-optimizer/claude-md.svg" alt="Measured on agentmods" 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 | $0.00888 | $0.00888 |
| Opus 5 | $0.00444 | $0.00444 |
| Sonnet 5 | $0.00178 | $0.00178 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
skill-optimizer CLAUDE.md 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 4d 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.
This is a copy
91% identical to skill-optimizer AGENTS.md — 5 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project Overview
skill-optimizer is a Docker workbench for running and grading agent skill eval cases. The current public CLI centers on run-case and run-suite.
The workbench gives an agent an isolated Docker /work directory, captures traces, and grades deterministic local outcomes from files, command logs, generated artifacts, or other workspace state.
Key Commands
npm run build
npm run typecheck
npm test
npx tsx src/cli.ts --help
npx tsx src/cli.ts run-case --help
npx tsx src/cli.ts run-suite --help
Important Files
src/cli.ts: public CLI entrypointsrc/workbench/: workbench case loading, suite loading, Docker runner, Pi agent, graders, and tracesdocker/workbench-runner.Dockerfile: generic non-root container image for setup, agent, grade, and cleanup phasesskills/skill-optimizer/SKILL.md: canonical distributable Agent Skillskills/skill-optimizer/references/workbench.md: detailed workbench schema and usage reference.claude-plugin/,.codex-plugin/,.cursor-plugin/,.opencode/: cross-agent plugin manifests and install support.agents/plugins/marketplace.json: Codex repo marketplace entry for the root plugingemini-extension.json,GEMINI.md: Gemini extension metadata and context fileexamples/workbench/: tracked example eval suitesREADME.md: provider-specific installation instructions for Claude Code, Codex, Cursor, OpenCode, Gemini CLI, and skill-only installsCONTRIBUTING.md: contributor workflow and current workbench invariants
Installation Docs
Keep the README installation section aligned with packaged plugin metadata:
- Claude Code:
.claude-plugin/plugin.jsonand.claude-plugin/marketplace.json - Codex:
.agents/plugins/marketplace.jsonand.codex-plugin/plugin.json - Cursor:
.cursor-plugin/plugin.jsonand.cursor/INSTALL.md - OpenCode:
.opencode/plugins/skill-optimizer.jsand.opencode/INSTALL.md - Gemini CLI:
gemini-extension.jsonandGEMINI.md - Skill-only installs:
npx skills add fastxyz/skill-optimizer --skill skill-optimizer ...
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.
- 4d ago First seen · 65 lines · 888 tokens per session scan A 337fa0abf6ee
skill-optimizer CLAUDE.md is an instructions file published in the GitHub repository fastxyz/skill-optimizer (77 stars, last pushed 3mo ago), licensed MIT. It adds 888 tokens to every session, about $0.0044 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to skill-optimizer AGENTS.md, differing in 5 lines, and is treated as a copy.
Other instructions, from other repositories
ClawBench AGENTS.md
AGENTS.md instructions for TIGER-AI-Lab/ClawBench, covering clawbench -- agent context, what this is, project structure, setup and 2. configure at least one model.
inspect-robots CLAUDE.md
Claude Code instructions for robocurve/inspect-robots, covering inspect robots — agent guide, the one big idea, layout, working here and out of scope (separate repos / plugins).
argus-validation-benchmarks CLAUDE.md
Instructions for pensar-x/argus-validation-benchmarks, covering project overview, what you're building, the goal, success criteria and what is apex?.
benchjack CLAUDE.md
Instructions for benchjack/benchjack, covering claude.md, project overview, tech stack, repository layout and common commands.
AgentBench-Live CLAUDE.md
Instructions for jackjin1997/AgentBench-Live, covering agentbench-live, project goal, strategy: credibility first, then ride the wave, current sprint scope (accepted from ceo review 2026-03-19) and deferred (todos).
agent-bench AGENTS.md
Instructions for cipherfoxie/agent-bench, covering agents, multi-agent contract for agent-bench, project ethos, rules and adding an experiment (the only common task).