benchmark SKILL.md skillA

benchmark from epicsagas/epic-harness is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add epicsagas/epic-harness/benchmark@git:20260904.0573d85

Pins git:20260904.0573d85 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
epicsagas/epic-harness
Path
.claude/skills/benchmark/SKILL.md
Versions recorded
1
Latest version
git:20260904.0573d85, committed Sep 4, 2026
Size
7,343 bytes
Repository stars
20
License
Apache-2.0

Executes Bare-vs-Epic A/B benchmarking, Ring 0 Guard 50 challenge, and full golden set evaluation for epic-harness. Orchestrates worker sessions, enforces strict workspace isolation, and synthesizes multi-dimensional comparison reports in TUI. Triggers: /benchmark, 'benchmark', 'a/b test', 'eval harness', 'smoke test', 'full eval'.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Benchmark — epic-harness A/B Evaluation & Golden Set Runner

**CRITICAL**: This is a repository-local developer evaluation skill. It is **NOT** included in the published `epic-harness` plugin bundle to prevent runtime context overhead in user projects.

---

## 1. When to Trigger
- Explicit `/benchmark`, `/benchmark full`, `/benchmark smoke`, or `/benchmark guard` commands
- User asks to "run A/B test", "evaluate harness", "run smoke test", or "benchmark all"
- Pre-release verification to confirm zero regressions and 100% guard interception rate
- Comparing new model profiles (e.g., Claude 3.7 Sonnet, GLM-5, GPT-4o) on Bare vs Epic

---

## 2. Command Reference & Execution Modes

| Command | Scope | What It Runs |
| :--- | :--- | :--- |
| **`/benchmark full`** (or `/benchmark all`) | **Full Suite (Recommended)** | 1) Ring 0 Guard 50 Challenge Suite<br>2) 5 Golden Set Tasks (Bare vs Epic A/B)<br>3) Master comparison report |
| **`/benchmark smoke`** | 5 Golden Set Tasks | Runs A/B evaluation across `task1` ~ `task5` |
| **`/benchmark task <name>`** | Single Task | Runs A/B evaluation on a specific task (e.g. `task3-security-auth-token`) |
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_bp22f4qemdbwdf7j/0bad1d9e8c08ab52ce9ca1641f11b48d54fe44eb4d0c76034852f458592f0fd5.json

Then /plugin install benchmark@markdownregistry-bp22f4qemdbwdf7j in Claude Code. It installs git:20260904.0573d85, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add epicsagas/epic-harness/benchmark@sha256:0bad1d9e8c08ab52

The line at the top of this page pins the label git:20260904.0573d85, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_bp22f4qemdbwdf7j.svg)](https://markdownregistry.com/a/art_bp22f4qemdbwdf7j)

1 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in epicsagas/epic-harness/benchmark since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of benchmark from somewhere else? Ask it: where did my benchmark come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 1 version of this file, committed on Sep 4, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20260904.0573d85 latest2026-09-04 0573d85 7,343 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7343 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

epicsagas/epic-harness · 20 stars · license Apache-2.0 · pushed 2026-11-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_bp22f4qemdbwdf7j
GET https://markdownregistry.com/api/v1/resolve?ref=epicsagas/epic-harness/benchmark
GET https://markdownregistry.com/api/v1/blob/0bad1d9e8c08ab52ce9ca1641f11b48d54fe44eb4d0c76034852f458592f0fd5

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from epicsagas/epic-harness

AGENTS.md AGENTS.md file
epicsagas/epic-harness · AGENTS.md
git:20261117.d9269a2 · audit A · 20 stars
CLAUDE.md CLAUDE.md file
epicsagas/epic-harness · CLAUDE.md
git:20260625.1c5e807 · audit B · 20 stars
_critic SKILL.md skill
epicsagas/epic-harness · skills/_critic/SKILL.md · HarnessX Critic (Tier 2.1) — adversarial review of evolved-skill proposals against trace evidence. Detects reward…
git:20260625.1c5e807 · audit A · 20 stars
_dispatch SKILL.md skill
epicsagas/epic-harness · skills/_dispatch/SKILL.md · Core router. Always active. Auto-invokes matching skill before every response. Runs confusion protocol on high-risk…
git:20261102.ac98b85 · audit A · 20 stars
agent-introspection SKILL.md skill
epicsagas/epic-harness · skills/agent-introspection/SKILL.md · Loop-breaking self-diagnosis. Use when 3+ consecutive failures occur, circular retries persist, or context overwhelms…
git:20260625.1c5e807 · audit A · 20 stars
audit SKILL.md skill
epicsagas/epic-harness · skills/audit/SKILL.md · Audit phase. Parallel review: code quality + security + tests. Semantic dedup of cross-mode findings. Outputs…
git:20261103.eb4d20b · audit A · 20 stars
commit SKILL.md skill
epicsagas/epic-harness · skills/commit/SKILL.md · Conventional Commits 1.0 generator. Stages relevant files, infers type(scope): description, never uses --no-verify.
git:20260625.1c5e807 · audit A · 20 stars
context SKILL.md skill
epicsagas/epic-harness · skills/context/SKILL.md · Working-state snapshot guidance. Restates task/files/decisions in one block so state survives context compaction…
git:20260831.ed1879c · audit A · 20 stars
council SKILL.md skill
epicsagas/epic-harness · skills/council/SKILL.md · 4-voice parallel deliberation (Architect · Skeptic · Pragmatist · Critic) for architecture, tech selection, or design…
git:20260625.1c5e807 · audit A · 20 stars
debug SKILL.md skill
epicsagas/epic-harness · skills/debug/SKILL.md · Systematic root-cause isolation for test failures, runtime errors, or unexpected behavior. Narrow hypothesis → verify →…
git:20260625.1c5e807 · audit A · 20 stars
discover SKILL.md skill
epicsagas/epic-harness · skills/discover/SKILL.md · Trigger: vague/unfocused request or solution-without-problem. Also invoked via /discover command. Reframes goal before…
git:20260625.1c5e807 · audit A · 20 stars
document SKILL.md skill
epicsagas/epic-harness · skills/document/SKILL.md · Documentation generator for public APIs, functions, and modules. Use when exports, signatures, or new modules are added…
git:20260625.1c5e807 · audit A · 20 stars

Every file in epicsagas/epic-harness

Other files named benchmark

benchmark SKILL.md skill
affaan-m/ecc · docs/ja-JP/skills/benchmark/SKILL.md · このスキルを使用して、パフォーマンスベースラインを測定し、PR前後の回帰を検出し、スタック代替案を比較します。
git:20260517.ec9ace9 · audit A · 305,967 stars
benchmark SKILL.md skill
garrytan/gstack · benchmark/SKILL.md · Web performance regression detection. (gstack)
v1.0.0 · audit A · 141,854 stars
benchmark SKILL.md skill
hashgraph-online/awesome-codex-plugins · plugins/Colin4k1024/tsp/skills/benchmark/SKILL.md · Use this skill to measure performance baselines, detect regressions before/after PRs, and compare stack alternatives.
git:20260512.6523792 · audit A · 1,584 stars
benchmark SKILL.md skill
hoangsonww/claude-code-agent-monitor · plugins/ccam-insights/skills/benchmark/SKILL.md · Benchmark one session (or a small recent set) against the rolling average using Agent Monitor data — cost, total…
git:20260804.9eab0d7 · audit A · 1,186 stars
benchmark SKILL.md skill
zhongkaifu/tensorsharp · InferenceWeb.Tests/Fixtures/MultiAgent/SKILL.md · Read independent service evidence for the multi-agent benchmark.
git:20260924.62d2787 · audit A · 679 stars
benchmark SKILL.md skill
jasonxudeveloper/nino · .claude/skills/benchmark/SKILL.md · How to measure Nino and what may be published - the .NET BenchmarkDotNet suite (quick mode, filters, v3 3.3.13 back to…
git:20261112.52bcc22 · audit A · 661 stars
benchmark SKILL.md skill
serejaris/personal-corp-os · skills/benchmark/SKILL.md · Use when choosing between engines or models for an agent pipeline and the answer must come from measurement on your own…
git:20260930.7ad9707 · audit A · 246 stars
benchmark SKILL.md skill
tongminglaic/ako4x · templates/skills/benchmark/SKILL.md · Reference for the active benchmark harness — what it IS and how it behaves (the active benchmark is flashinfer-bench)…
git:20260531.0fd4b5f · audit A · 88 stars

Browse by kind, by grade A, or by owner.