harness-first SKILL.md skillA
harness-first from peterpme/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add peterpme/skills/harness-first@git:20261111.fb4a9f9Pins git:20261111.fb4a9f9 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- peterpme/skills
- Path
harness-first/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261111.fb4a9f9, committed Nov 11, 2026
- First version recorded
- Nov 9, 2026
- Size
- 4,662 bytes
- Repository stars
- 28
- License
- none declared
Use when a change is meant to move a number: faster, smaller, smoother, cheaper or less flaky (startup, jank, frame drops, bundle size, memory, CI time, API cost, eval scores, any hill climb), or when Peter asks how you know it is faster. Measure a baseline first, then report the change against it. Not for a bug with a repro.
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
# Harness first A number nobody measured before the change is a guess, and a guess in a PR body is a claim nobody can check. Peter's rule: no change meant to improve a number lands without a committed baseline from a harness in the repo. ## 1. Name the number Before reading code for fixes, write down: the metric and its unit (late frames per scenario, cold start ms, bundle bytes, p95 latency, flaky failures per 100 runs), which direction is better, the environment users run (physical device model, release build, production bundler, real data), and Peter's target if he gave one. This goes in the contract's acceptance checks as "baseline X on base SHA, after Y on head SHA, same harness, same environment". ## 2. Find the harness before writing one Search, and record what you found and why it fits or not: - `scripts/`, `tools/`, `bench*`, `perf*`, `profil*`, `verify*`, package and task-runner scripts, CI workflows. - The repo's agents file and docs, and the skills installed for the stack (profilers, e2e recorders). - Earlier PRs: `gh pr list --search "perf OR benchmark OR baseline" --state all`. A PR with a before-and-after table names its harness. …
Read the whole file at its exact version.
How to install
claude plugin marketplace add https://markdownregistry.com/mp/a/art_554l4vmn4likdomo/1c1f70a713b763bf82466551d6c3bbdf7912bfe538cecf961b54d3319f0e1c64.json
Then /plugin install harness-first@markdownregistry-554l4vmn4likdomo in Claude Code. It installs git:20261111.fb4a9f9, the one graded A here, pinned to the commit it was graded at, and leaves it there.
mdr add peterpme/skills/harness-first@sha256:1c1f70a713b763bfThe line at the top of this page pins the label git:20261111.fb4a9f9, 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.
[](https://markdownregistry.com/a/art_554l4vmn4likdomo)
6 badge image fetches in 30 days. What the badge shows.
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it: what changed in peterpme/skills/harness-first 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 harness-first from somewhere else? Ask it: where did my harness-first 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 2 versions of this file, between Nov 9, 2026 and Nov 11, 2026, about one every 3 days.
Watch this file (sign in, one email per new version)
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261111.fb4a9f9 latest | 2026-11-11 | fb4a9f9 | 4,662 B | A | view · diff |
| git:20261109.f86bb14 | 2026-11-09 | f86bb14 | 4,899 B | A | view |
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.
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.
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.
Installed this file, say at .claude/skills/harness-first/SKILL.md? Drop it here to learn which saved version you have and what changed since. Your browser works out its SHA-256 fingerprint and sends only that; the file itself never leaves your computer.
Or paste its contents
Your agent can run this same check on the agent markdown files you have installed, up to 50 in one ask. Add the registry once:
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it to check the files you have installed. No key and no account.
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
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4662 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
peterpme/skills · 28 stars · license none declared · pushed 2026-11-16 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_554l4vmn4likdomo GET https://markdownregistry.com/api/v1/resolve?ref=peterpme/skills/harness-first GET https://markdownregistry.com/api/v1/blob/1c1f70a713b763bf82466551d6c3bbdf7912bfe538cecf961b54d3319f0e1c64
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.