model-bench SKILL.md skillA
model-bench from nateslabach/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add nateslabach/skills/model-bench@git:20260723.7e8d84dPins git:20260723.7e8d84d in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- nateslabach/skills
- Path
skills/model-bench/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260723.7e8d84d, committed Jul 23, 2026
- First version recorded
- Jul 21, 2026
- Size
- 4,768 bytes
- Repository stars
- 6
- License
- MIT
Run a 3-leg evaluation against a newly released LLM. Leg 1 is trap questions with deterministic answers, leg 2 is an agentic orchestration task with a planted failure, leg 3 is a brownfield feature build in a real repo. Use when the user wants to vibe-check, test, evaluate, or compare a new frontier model, or mentions model-bench, model vibe check, or launch-day protocol.
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
# model-bench 3 legs, each aimed at a different failure mode: 1. **Trap questions**: does it think, or pattern-match to training data? Deterministic answers, grades in seconds. 2. **Orchestration**: can it plan, delegate, and recover when a step fails (including a planted trap)? 3. **Brownfield build**: can it ship a feature into an existing codebase without breaking things 2 files away? Each leg scores 0-5. Total out of 15. ## Contamination rules (read first) - The model under test must NEVER see gold answers or learn about the planted trap. If it does, that leg is void. - **Private answer key** lives outside this repo: `~/proctor/model-bench/answer-key.md` (or `grading/answer-key.local.md`, gitignored). Public stub: [grading/answer-key.md](grading/answer-key.md). Legs 2–3 checklists: [grading/rubrics.md](grading/rubrics.md). - This skill runs in a **proctor session** (Nate plus a model he already trusts). The model under test only ever receives the task prompts — never this skill folder, never the private key. - **Never use this repo as the target repo** for legs 2–3. …
Read the whole file at its exact version.
How to install
mdr add nateslabach/skills/model-bench@sha256:1912647493d5d57fThe line at the top of this page pins the label git:20260723.7e8d84d, 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_ddbl4chaygou7ctq)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Jul 21, 2026 and Jul 23, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260723.7e8d84d latest | 2026-07-23 | 7e8d84d | 4,768 B | A | view · diff |
| git:20260723.746f370 | 2026-07-23 | 746f370 | 4,737 B | A | view · diff |
| git:20260721.97dc2a3 | 2026-07-21 | 97dc2a3 | 4,131 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 (4768 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
nateslabach/skills · 6 stars · license MIT · pushed 2026-09-29 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ddbl4chaygou7ctq GET https://markdownregistry.com/api/v1/resolve?ref=nateslabach/skills/model-bench GET https://markdownregistry.com/api/v1/blob/1912647493d5d57f78394083d756f938b3a9c12696893c8f05cc68f3119b3866
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.