AGENTS.md@crates/wenlan-core/src/evalA

This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.

AGENTS.md@crates/wenlan-core/src/eval from wenlan-app/wenlan is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add wenlan-app/wenlan/crates/wenlan-core/src/eval/AGENTS.md@git:20260809.87beaaa

Pins git:20260809.87beaaa in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
wenlan-app/wenlan
Path
crates/wenlan-core/src/eval/AGENTS.md
Versions recorded
5
Latest version
git:20260809.87beaaa, committed Aug 9, 2026
First version recorded
Jul 18, 2026
Size
1,054 bytes
Repository stars
85
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

# Rust eval runners

Applies under `crates/wenlan-core/src/eval/` in addition to the root and
`crates/wenlan-core/AGENTS.md` instructions.

- Match the existing ephemeral or cached runner shape; do not mix their source-id,
  seeding, or artifact contracts.
- Start with a smoke-sized, category-aware run. Use a full benchmark only when the
  decision needs that statistical power; repeated full runs are not a default gate.
- Refuse experiments whose required substrate is absent, stale, consolidated across
  questions when isolation is required, or otherwise confounded.
- A/B arms must stamp their environment and differ only in the intended treatment.
  Run the matching A/A/no-op control when the analyzer requires a noise floor.
- Retrieval drift goldens detect change, not correctness. Refresh them only after the
  labeled eval is green and the ranking change is intentional.

Detailed runner commands, cache flags, power guidance, methodology, and receipts live
in `REFERENCE.md`. Fixture and artifact handling lives in `app/eval/REFERENCE.md`.

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add wenlan-app/wenlan/crates/wenlan-core/src/eval/AGENTS.md@sha256:61d083fcadfecb59

The line at the top of this page pins the label git:20260809.87beaaa, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_tlxu2zfq3qy3a37n.svg)](https://markdownregistry.com/a/art_tlxu2zfq3qy3a37n)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Jul 18, 2026 and Aug 9, 2026, about one every 6 days.

versioncommittedcommitsizeaudit
git:20260809.87beaaa latest2026-08-09 87beaaa 1,054 BA view · diff
git:20260805.b6733982026-08-05 b673398 31,169 BA view · diff
git:20260802.14929452026-08-02 1492945 37,188 BA view · diff
git:20260725.1d7b67e2026-07-25 1d7b67e 37,112 BA view · diff
git:20260718.4fd6df72026-07-18 4fd6df7 37,117 BA view

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (1054 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

GitHub

wenlan-app/wenlan · 85 stars · license Apache-2.0 · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_tlxu2zfq3qy3a37n
GET https://markdownregistry.com/api/v1/resolve?ref=wenlan-app/wenlan/crates/wenlan-core/src/eval/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/61d083fcadfecb594d7e0d7439d6dc407b04a901bcacc43ed145e4eeac9699df

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 wenlan-app/wenlan

prove SKILL.md skill
wenlan-app/wenlan · .claude/skills/prove/SKILL.md · Per-surface verification loops for wenlan — daemon, cli, mcp, plugin, suite strength (mutation), behavior trace, weekly…
git:20261019.1b4e3ca · audit A · 85 stars
run-wenlan-app SKILL.md skill
wenlan-app/wenlan · .claude/skills/run-wenlan-app/SKILL.md · Build, launch, screenshot, and drive the wenlan-app Tauri desktop app in dev mode on macOS (WKWebView) or Windows…
git:20261020.866f6de · audit A · 85 stars
run-wenlan SKILL.md skill
wenlan-app/wenlan · .claude/skills/run-wenlan/SKILL.md · Build, launch, and stop the wenlan daemon (wenlan-server) for local dev and verification. Use when asked to run or…
git:20260903.66f0580 · audit B · 85 stars
verify SKILL.md skill
wenlan-app/wenlan · .claude/skills/verify/SKILL.md · Drive/evidence recipe for verifying wenlan changes at their real surfaces (daemon HTTP, CLI, MCP stdio). The handle…
git:20260903.66f0580 · audit A · 85 stars
AGENTS.md AGENTS.md file
wenlan-app/wenlan · AGENTS.md
git:20261011.84b0dcd · audit B · 85 stars
CLAUDE.md CLAUDE.md file
wenlan-app/wenlan · CLAUDE.md
git:20260512.48c7daa · audit A · 85 stars
AGENTS.md@app AGENTS.md file
wenlan-app/wenlan · app/AGENTS.md
git:20260923.92db83c · audit A · 85 stars
CLAUDE.md@app CLAUDE.md file
wenlan-app/wenlan · app/CLAUDE.md
git:20260816.95cb545 · audit B · 85 stars
AGENTS.md@app/eval AGENTS.md file
wenlan-app/wenlan · app/eval/AGENTS.md
git:20260816.95cb545 · audit A · 85 stars
CLAUDE.md@app/eval CLAUDE.md file
wenlan-app/wenlan · app/eval/CLAUDE.md
git:20260605.d6cfdd6 · audit B · 85 stars
AGENTS.md@crates/wenlan-core AGENTS.md file
wenlan-app/wenlan · crates/wenlan-core/AGENTS.md
git:20260823.54c8a7e · audit A · 85 stars
CLAUDE.md@crates/wenlan-core CLAUDE.md file
wenlan-app/wenlan · crates/wenlan-core/CLAUDE.md
git:20260623.eda6386 · audit B · 85 stars

Every file in wenlan-app/wenlan

Other files named AGENTS.md@crates/wenlan-core/src/eval

AGENTS.md@crates/wenlan-core/src/eval AGENTS.md file
7xuanlu/wenlan · crates/wenlan-core/src/eval/AGENTS.md
git:20260809.87beaaa · audit A · 84 stars

Browse by kind, by grade A, or by owner.