benchmark

benchmark is a skill for Claude Code from vasuag09/harness-claude. It costs 88 tokens per session (1,136 once invoked), scanned A, original, MIT.

A repeatable test that compares a coding-agent component with and without the component across separate Git worktrees, which are isolated copies of a repository.

In plain words
What is it for?
Use it to evaluate a skill, agent, or rule before keeping or removing it. It reports pass@k and pass^k results from repeated trials.
Why use it?
It replaces opinions about usefulness with evidence about whether a task works at least once and whether it works consistently.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/eval/benchmark.js --component <name> --task '<cmd>' [--score '<cmd>'] [--k 5].

Part of the harness-claude plugin — 32 skills, 8 agents, 6 hooks, 3 MCP servers shipped together

Good fit Use it to evaluate a skill, agent, or rule before keeping or removing it. It reports pass@k and pass^k results from repeated trials.

Compare 6 skills from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/vasuag09/harness-claude
agentmods
npx agentmods add skills/vasuag09/harness-claude/benchmark

Made for: Claude Code.

Or install harness-claude, the plugin that ships this one along with the rest of its 32 skills, 8 agents, 6 hooks, 3 MCP servers.

Wrote 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.

agentmods badge for benchmark

README.md
[![agentmods](https://agentmods.dev/badge/skills/vasuag09/harness-claude/benchmark.svg)](https://agentmods.dev/skills/vasuag09/harness-claude/benchmark)
Your own site
<a href="https://agentmods.dev/skills/vasuag09/harness-claude/benchmark"><img src="https://agentmods.dev/badge/skills/vasuag09/harness-claude/benchmark.svg" alt="Measured on agentmods" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,136 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00088 $0.01136
Opus 5 $0.00044 $0.00568
Sonnet 5 $0.00018 $0.00227
Haiku 4.5 $0.00009 $0.00114

Measured 7d ago against content hash 3a2bbcc16caf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

benchmark 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 7d 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/benchmark/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/benchmark — does this component earn its keep?

Goal: replace opinion with evidence. Run a task k times with a named component enabled and k times without it, each trial in its own throwaway git worktree, then compare reliability. Report pass@k (passed in ≥1 trial — "can it work") and pass^k (passed in all k trials — "does it work reliably"), and a verdict.

Opt-in. No default-pipeline skill or hook invokes /benchmark. It forks git worktrees and (when you supply a real task) spawns work k×2 times — always an explicit, deliberate run. Git boundary: it only git worktree add/remove (an isolated sandbox); it never commits, pushes, or branches the working tree.

When to run

  • You want to decide whether a skill / agent / rule is worth keeping (keep-vs-cut on data).
  • A /extract proposal sits at R5 MANUAL and you want a real empirical signal — benchmark it with --component <draft-name> so the result lands where R5 looks.

The harness contract

scripts/eval/benchmark.js is generic: it knows nothing about your component. It toggles the component only through env vars the task command honors, for each trial:

env meaning
HARNESS_COMPONENT the component name (label)
HARNESS_COMPONENT_ENABLED 1 (with) · 0 (without)
HARNESS_TRIAL 0-based trial index

A trial passes iff its score command exits 0. Default score = the task's own exit code; recommended = node scripts/eval/checkpoint.js <spec> so a trial is scored against a spec's acceptance criteria (reusing the v0.4 gate).

Do this

  1. Define the task. Decide what "doing the task" means and write a command that performs it in the current worktree, reading HARNESS_COMPONENT_ENABLED to enable/disable the component under test (e.g. include the skill's guidance only when =1). For a model-driven task, the command drives a subagent; for a deterministic check, any shell script works.
  2. Define scoring. Either let the task's exit code be the signal, or pass --score (e.g. checkpoint.js against the task's spec) so PASS/FAIL is judged against acceptance criteria.
  3. Run the benchmark:
    node scripts/eval/benchmark.js --component <name> --task '<cmd>' [--score '<cmd>'] [--k 5]
    
    Exit 0 = pass verdict (component earns its keep) · 1 = fail verdict (no reliability gain) · 2 = usage/setup error (no --task, not a git repo, no HEAD commit).
  4. Read the result. The run prints both cohorts' pass@k / pass^k / success-rate and the verdict, and writes .claude/eval/benchmarks/<slug>.json (<slug> = the component name). The verdict is: earns its keep iff with.successRate > without.successRate or (with.passCaret && !without.passCaret).
  5. Act on it. Recommend keep or cut with the numbers. For an /extract proposal, the artifact now feeds R5: re-run node scripts/eval/extract-rubric.js <draft> and R5 reports PASS/FAIL from the benchmark instead of MANUAL. Promotion into skills/ is still a human call (R4 + your approval) — a passing benchmark never auto-promotes.

Read the full file on GitHub · 75 lines

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. 7d ago First seen · 75 lines · 88 tokens per session scan A 3a2bbcc16caf

Subscribe to this mod's changes

benchmark is a skill published in the GitHub repository vasuag09/harness-claude (2 stars, last pushed 2mo ago), licensed MIT. It adds 88 tokens to every session and 1,136 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

ci-tests

Run the test suite for the current repo, auto-detecting Python (pytest/uv), Node (vitest/pnpm), or Rust (cargo test).

FlorianBruniaux/claude-code-plugins · 35 tokens

git-worktree

Create isolated git worktrees for feature development without switching branches.

FlorianBruniaux/claude-code-plugins · 15 tokens

git-worktree-status

Check status of background verification tasks running in a git worktree.

FlorianBruniaux/claude-code-plugins · 17 tokens

typescript-providers

Implement, modify, test, or document TypeScript provider packages under ts/packages/providers, including framework adapters for OpenAI, Anthropic, Google, LangChain, Mastra, Vercel, LlamaIndex, Cloudflare, and Claude Agent SDK. Use for provider-specific TS work; do not use for core-only changes.

ComposioHQ/composio · 70 tokens

typescript-sdk

Implement or modify TypeScript SDK behavior in @composio/core or shared TypeScript packages, including tools, toolkits, sessions, auth configs, connected accounts, modifiers, and generated SDK surfaces. Use for TS runtime/API work; pair with typescript-testing for verification and cross-sdk-parity when Python must…

ComposioHQ/composio · 67 tokens

typescript-testing

Select and run TypeScript SDK verification for packages, examples, type checks, linting, builds, Vitest suites, and runtime E2E tests. Use when adding tests, diagnosing TypeScript CI, choosing a focused test command, or validating TypeScript package changes. Do not use for Python-only checks.

ComposioHQ/composio · 65 tokens