skill-optimizer

An evaluation workbench for testing AI-agent skills. It runs user-like tasks in an isolated Docker workspace, records the agent's actions, and grades the resulting files or other outcomes.

In plain words
What is it for?
Use it to create and run evaluation cases and suites, test skills across models, inspect traces, and use deterministic graders to check results.
Why use it?
It helps you measure whether a skill works reliably instead of judging it from a few conversations. The recorded trace also helps investigate failures.

Skill for Claude CodeCodex

Part of the skill-optimizer plugin — 2 skills shipped together

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.

agentmods
npx agentmods add skills/fastxyz/skill-optimizer/skill-optimizer
Any agent
npx skills add fastxyz/skill-optimizer --skill skill-optimizer
Clone the repo
git clone --depth 1 https://github.com/fastxyz/skill-optimizer

Made for: Claude Code, Codex.

Or install skill-optimizer, the plugin that ships this one along with the rest of its 2 skills.

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,349 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00052 $0.02349
Opus 5 $0.00026 $0.01175
Sonnet 5 $0.00010 $0.00470
Haiku 4.5 $0.00005 $0.00235

Measured 3d ago against content hash 8875c9505df1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-optimizer 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 3d 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/skill-optimizer/SKILL.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

skill-optimizer

skill-optimizer is an eval workbench for agent skills. It runs a model in an isolated Docker /work directory, provides skills/references as normal workspace files, captures an agent trace, and grades deterministic local outcomes.

Use this skill as the source of truth for authoring eval suites in this repo. Detailed schema and patterns are in references/workbench.md.

Core Model

  • A case is one user-like task plus one or more deterministic graders.
  • A suite is a set of cases and OpenRouter models to run as a matrix.
  • references are copied into /work before the agent starts; this is where eval skills live.
  • The agent phase sees /work only. It cannot see /case, /results, graders, hidden answers, or hidden metadata.
  • Cases can define mcpServers; these are exposed through a workbench mcp command during the agent phase.
  • Graders run after the agent with /case, /work, and /results mounted.
  • trace.jsonl is the debugging source for what the agent saw, said, and did.

Commands

Goal Command
Install deps npm install
Build CLI npm run build
Run one case npx tsx src/cli.ts run-case <case.yml>
Run one case across models npx tsx src/cli.ts run-case <case.yml> --models openrouter/google/gemini-2.5-flash,openrouter/openai/gpt-5.4
Run a suite npx tsx src/cli.ts run-suite <suite.yml>
CLI help npx tsx src/cli.ts --help

Rules:

  • Use only openrouter/... model refs.
  • OPENROUTER_API_KEY is required for real model runs.
  • run-suite uses models: from suite.yml; it has no model override flag.
  • run-case can use its case model: or --model / --models.
  • Docker image default is skill-optimizer-workbench:local.

Install This Skill

This repository ships one canonical skill at skills/skill-optimizer/SKILL.md plus plugin metadata for Claude Code, OpenCode, Codex, Cursor, and Gemini.

Install the skill for common agents with:

npx skills add fastxyz/skill-optimizer --skill skill-optimizer -a claude-code -a opencode -a codex -a cursor

Read the full file on GitHub · 211 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. 3d ago First seen · 211 lines · 52 tokens per session scan A 8875c9505df1

Subscribe to this mod's changes

skill-optimizer is a skill published in the GitHub repository fastxyz/skill-optimizer (77 stars, last pushed 3mo ago), licensed MIT. It adds 52 tokens to every session and 2,349 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 2026-08-30.

Related

Other skills, from other repositories

ceo-setup

One-time onboarding for the executive/manager commitment workflow — delegation-heavy, meeting prep, decision capture, morning and evening digests. Creates a commitments project and installs two dashboard widgets. After successful setup this skill is excluded from selection until the marker file is deleted.

suyoumo/ClawProBench · 60 tokens

developer-setup

One-time onboarding for the developer workflow — installs github-workflow missions, creates the commitments workspace, registers per-repo projects, writes calibration memories. After successful setup this skill is excluded from selection until the marker file is deleted.

suyoumo/ClawProBench · 49 tokens

portfolio

Cross-chain DeFi portfolio discovery, rebalancing suggestions, and NEAR Intent construction. Activates when the user pastes a wallet address or asks about yield/positions/rebalancing. Bootstraps a per-user "portfolio" project, aggregates positions across all the user's addresses inside one project, and offers a…

suyoumo/ClawProBench · 69 tokens

code-review

Paranoid architect review of code changes for bugs, security, missing tests, and undocumented assumptions. Works on local git diffs OR a GitHub pull request (e.g. owner/repo N). For PRs, can post findings as line-level review comments.

suyoumo/ClawProBench · 57 tokens

commitment-setup

One-time setup for the commitments tracking system. Creates workspace structure, schema docs, and installs triage and digest missions. Excluded from activation once projects/commitments/README.md exists in the workspace (the file this skill writes as its first step).

suyoumo/ClawProBench · 58 tokens

content-creator-setup

One-time onboarding for the content creator workflow — content pipeline stages, trend expiration, cross-platform cascades, heavy idea parking. After successful setup this skill is excluded from selection until the marker file is deleted.

suyoumo/ClawProBench · 47 tokens