AGENTS.md@evalsA
AGENTS.md@evals from b-mendoza/agent-skills is an AGENTS.md file: the standing instructions coding agents read in that repo.
mdr add b-mendoza/agent-skills/evals/AGENTS.md@git:20260804.71e34dbPins git:20260804.71e34db in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 14 of 14 checks passed
- Kind
- AGENTS.md file
- Repository
- b-mendoza/agent-skills
- Path
evals/AGENTS.md- Versions recorded
- 5
- Latest version
- git:20260804.71e34db, committed Aug 4, 2026
- First version recorded
- Jul 30, 2026
- Size
- 1,803 bytes
- Repository stars
- 3
- License
- none declared
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
# Agent Guide — evals Nearest guide for the eval suite: a self-contained pnpm workspace that runs skills against fixture repos through the Agent SDK. ## Toolchain - Node `24.19.0` (see [`.nvmrc`](./.nvmrc)); TypeScript runs from source — there is no build step. - `pnpm` is the package manager (`pnpm install` once, from this directory). ## Always - Lint check (run after a substantive change): `pnpm lint` (tsc, eslint, oxlint, oxfmt `--check`); `pnpm fix` applies the auto-fixes. - Test suite (run before committing): `pnpm test` (offline vitest). - [`report.md`](./report.md) is a committed, generated artifact; only a real eval run rewrites it. - Eval runs spend real money and require explicit user approval. Answer anything a free check can answer with a free check — see [`docs/verification.md`](./docs/verification.md). ## Open when relevant (long-lived) - [TypeScript design conventions](docs/agent/conventions.md) — design guidance such as erasable syntax, factory functions, and boundary parsing. - [Testing — evals specifics](docs/agent/testing-principles.md) — Vitest assertion practices and Agent SDK test boundaries. …
Read the whole file at its exact version.
How to install
mdr add b-mendoza/agent-skills/evals/AGENTS.md@sha256:3e75f738e22c3ff8The line at the top of this page pins the label git:20260804.71e34db, 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_h7kxa5p452rb2baw)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 30, 2026 and Aug 4, 2026, about one every day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260804.71e34db latest | 2026-08-04 | 71e34db | 1,803 B | A | view · diff |
| git:20260804.ee907fb | 2026-08-04 | ee907fb | 1,803 B | A | view · diff |
| git:20260801.2437851 | 2026-08-01 | 2437851 | 2,386 B | A | view · diff |
| git:20260731.7a14d18 | 2026-07-31 | 7a14d18 | 2,932 B | A | view · diff |
| git:20260730.e5e9792 | 2026-07-30 | e5e9792 | 2,912 B | A | view |
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (1803 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
b-mendoza/agent-skills · 3 stars · license none declared · pushed 2026-10-17 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_h7kxa5p452rb2baw GET https://markdownregistry.com/api/v1/resolve?ref=b-mendoza/agent-skills/evals/AGENTS.md GET https://markdownregistry.com/api/v1/blob/3e75f738e22c3ff8471d1d76970b4c8ba28b634f766f82fdfda113584e72bf3e
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: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.
More from b-mendoza/agent-skills
Every file in b-mendoza/agent-skills