replay-app-harness SKILL.md skillA
replay-app-harness 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/replay-app-harness@git:20261027.533318ePins git:20261027.533318e 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/replay-app-harness/SKILL.md- Versions recorded
- 3
- Latest version
- git:20261027.533318e, committed Oct 27, 2026
- First version recorded
- Jul 22, 2026
- Size
- 4,206 bytes
- Repository stars
- 19
- License
- MIT
Use when a coding agent has edited a user's LLM app and wants a regression verdict on the frozen benchmark tasks — "did my code change regress the eval", "run my actual app against the benchmark", "author an app-harness.json". Drafts the understudy.app_harness.v1 sidecar from the user's repo, queues an app_replay run, and reads the honest (marked-anomaly, never fabricated) rows.
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
# Replay the user's app on frozen benchmark tasks Model arms answer "what would model X do?". The `app_replay` arm answers "what does the user's app, as the code currently exists, do on the same frozen tasks?" — the regression check to run after editing the user's code. Full reference: `docs/app-harness.md` in this repo; sidecar schema: `schemas/understudy.app_harness.v1.schema.json`. ## 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 runs execute --benchmark <benchmark-dir> ``` ## Safety Gates - **The harness launches the user's own code as a subprocess.** Only put commands in `app-harness.json` that the developer showed you or approved; never invent entrypoints. Show the drafted sidecar and get approval before the first run. - **LLM traffic is pinned to the Orchestra gateway.** The executor's redirect env vars win over the harness's `env` — do not attempt to route around them, and say so if the app hard-codes a provider base URL. - **The app may mutate real state.** Before queueing, confirm with the …
Read the whole file at its exact version.
How to install
mdr add understudylabs/orchestra-agent-tools/replay-app-harness@sha256:da4eb283953f5c1fThe line at the top of this page pins the label git:20261027.533318e, 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_fnh5jfdnbaake5hz)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Jul 22, 2026 and Oct 27, 2026, about one every 49 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261027.533318e latest | 2026-10-27 | 533318e | 4,206 B | A | view · diff |
| git:20261027.3c367b0 | 2026-10-27 | 3c367b0 | 4,207 B | A | view · diff |
| git:20260722.0fa4474 | 2026-07-22 | 0fa4474 | 4,209 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 (4206 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_fnh5jfdnbaake5hz GET https://markdownregistry.com/api/v1/resolve?ref=understudylabs/orchestra-agent-tools/replay-app-harness GET https://markdownregistry.com/api/v1/blob/da4eb283953f5c1f41c63d4f4eec571e0cb11d214252d9039d34cbfa5e958ef9
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.