AGENTS.md@app/evalA
AGENTS.md@app/eval from 7xuanlu/wenlan is an AGENTS.md file: the standing instructions coding agents read in that repo.
mdr add 7xuanlu/wenlan/app/eval/AGENTS.md@git:20260816.95cb545Pins git:20260816.95cb545 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 14 of 14 checks passed
- Kind
- AGENTS.md file
- Repository
- 7xuanlu/wenlan
- Path
app/eval/AGENTS.md- Versions recorded
- 5
- Latest version
- git:20260816.95cb545, committed Aug 16, 2026
- First version recorded
- Jun 25, 2026
- Size
- 950 bytes
- Repository stars
- 84
- License
- Apache-2.0
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
# Eval fixtures and artifacts Applies under `app/eval/` in addition to the root instructions. - Treat cached scenario databases and model-backed baselines as external, reproducible artifacts. - Use smoke limits for wiring checks and the smallest representative subset for method checks. - Do not cite a score without the producing commit, environment/schema stamp, sample size, per-run receipt, and the correct pipeline layer. - Never compare arms produced from different substrates or silently migrate/wipe a cache without the explicit owning flag and preflight. ## eval citation discipline External numbers must come from retained receipts, not terminal recollection or an average with missing runs. State skipped legs and unavailable gates explicitly. Commands, cache flags, layouts, bench-specific methodology, and historical receipts live in `REFERENCE.md`. Rust runner internals live in `crates/wenlan-core/src/eval/REFERENCE.md`.
Read the whole file at its exact version.
How to install
mdr add 7xuanlu/wenlan/app/eval/AGENTS.md@sha256:bc84e2ca59bf7971The line at the top of this page pins the label git:20260816.95cb545, 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_fyiv3qsoj42qwp4q)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jun 25, 2026 and Aug 16, 2026, about one every 13 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260816.95cb545 latest | 2026-08-16 | 95cb545 | 950 B | A | view · diff |
| git:20260809.87beaaa | 2026-08-09 | 87beaaa | 1,206 B | A | view · diff |
| git:20260718.4fd6df7 | 2026-07-18 | 4fd6df7 | 15,639 B | A | view · diff |
| git:20260630.d072a38 | 2026-06-30 | d072a38 | 12,646 B | A | view · diff |
| git:20260625.b3a7373 | 2026-06-25 | b3a7373 | 12,646 B | A | view |
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (950 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
7xuanlu/wenlan · 84 stars · license Apache-2.0 · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_fyiv3qsoj42qwp4q GET https://markdownregistry.com/api/v1/resolve?ref=7xuanlu/wenlan/app/eval/AGENTS.md GET https://markdownregistry.com/api/v1/blob/bc84e2ca59bf7971411d364b0c648dc9b29acbff490ff84dbd7637db5d3535ed
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.