operate-benchmark-lab SKILL.md skillA
operate-benchmark-lab from understudylabs/orchestra-agent-tools is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add understudylabs/orchestra-agent-tools/operate-benchmark-lab@git:20261027.3c367b0Pins git:20261027.3c367b0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- understudylabs/orchestra-agent-tools
- Path
skills/operate-benchmark-lab/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261027.3c367b0, committed Oct 27, 2026
- First version recorded
- Jul 22, 2026
- Size
- 16,238 bytes
- Repository stars
- 19
- License
- MIT
Use when a coding agent must operate the full benchmark lifecycle over local benchmark dirs — "build a benchmark from my traces and run models on it", "review and calibrate the eval", "queue a prompt experiment", "is an executor running", "read the rigor report". Covers traces → build-benchmark → review/feedback → calibration floors → candidate and prompt-override runs → rigor/CI reading → app-replay regression, via the benchmarks MCP server or CLI verbs, plus the run-executor daemon lifecycle.
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
# Operate the benchmark lab
The operator's manual for the whole benchmark/experiment lifecycle a coding
agent can drive end to end. Two interfaces over the same sidecar files:
the **benchmarks MCP server** (preferred for agents — same validation code as
the hub API) and the **CLI verbs**. Execution always happens in a separate
executor process; the MCP server and hub never run models. Command matrix,
artifact map, and daemon details in [`reference.md`](reference.md); the tool
table and agent loop in `docs/agent-operator-surface.md`.
## Resolve CLI
Prefer the installed `orchestra` binary. If it is unavailable inside a repo
checkout, run through the package script:
```sh
npm run build
node dist/bin.js benchmarks mcp --root <dir>
```
MCP registration (Claude Code `~/.claude.json` → `mcpServers`):
`{ "understudy-benchmarks": { "type": "stdio", "command": "understudy", "args": ["benchmarks", "mcp"] } }`
— or let the CLI write it: `claude mcp add --scope user understudy-benchmarks -- orchestra benchmarks mcp`
(`--scope user` matches the top-level entry above; the default `local` scope is per-project).
Default root `~/.understudy/benchmarks`; add `--root` per extra directory.
…Read the whole file at its exact version.
How to install
mdr add understudylabs/orchestra-agent-tools/operate-benchmark-lab@sha256:f780a1423e8de471The line at the top of this page pins the label git:20261027.3c367b0, 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_ngezhzpdh7kdcnh4)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 22, 2026 and Oct 27, 2026, about one every 24 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261027.3c367b0 latest | 2026-10-27 | 3c367b0 | 16,238 B | A | view · diff |
| git:20261020.17ad730 | 2026-10-20 | 17ad730 | 16,259 B | A | view · diff |
| git:20260803.d9f9c16 | 2026-08-03 | d9f9c16 | 15,594 B | A | view · diff |
| git:20260723.3f483e8 | 2026-07-23 | 3f483e8 | 13,915 B | A | view · diff |
| git:20260722.ceb32f7 | 2026-07-22 | ceb32f7 | 8,893 B | A | view |
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 (16238 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
understudylabs/orchestra-agent-tools · 19 stars · license MIT · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ngezhzpdh7kdcnh4 GET https://markdownregistry.com/api/v1/resolve?ref=understudylabs/orchestra-agent-tools/operate-benchmark-lab GET https://markdownregistry.com/api/v1/blob/f780a1423e8de471e7d7fb3d9e074244e4bc720e8157ac162128be9126d18be8
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.