AGENTS.md@testsA
AGENTS.md@tests from amd-agi/aklr is an AGENTS.md file: the standing instructions coding agents read in that repo.
mdr add amd-agi/aklr/tests/AGENTS.md@git:20261118.7e9cff8Pins git:20261118.7e9cff8 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 14 of 14 checks passed
- Kind
- AGENTS.md file
- Repository
- amd-agi/aklr
- Path
tests/AGENTS.md- Versions recorded
- 2
- Latest version
- git:20261118.7e9cff8, committed Nov 18, 2026
- First version recorded
- Nov 18, 2026
- Size
- 2,540 bytes
- Repository stars
- 15
- License
- MIT
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
# Tests 1. **TDD loop.** Load the `aklr:tdd` skill before writing or changing a test here, and follow its loop. 2. **Test at seams.** A test imports and calls only seams. A seam is a name imported from a path with no `_` segment: defined in a public module, or exported by a public package's `__init__` (`from aklr.core.runtime.dispatch import DispatcherRegistry`, though it lives in `_registry.py`). A name reached only through a `_` module, and any `_` attribute, is not one. Code behind a seam is tested through the seam. These are the `aklr:tdd` skill's pre-agreed seams: write the test at one directly; confirm with the user only an interface still undecided. 3. **GPU tests run on a GPU.** Tests marked `gpu` or `gfx950` are skipped on a machine without that GPU (`conftest.py`), and a skip is neither red nor green: run them on a GPU, a remote node from the `remote-gpu` skill if none is local. 4. **Layout.** `tests/<path>/test_<what>.py` tests code in `aklr/<path>/`; every directory has an `__init__.py`. The one exception: `tests/benchmarks/test_agentx_*.py` test `benchmarks/agentx/`, …
Read the whole file at its exact version.
How to install
mdr add amd-agi/aklr/tests/AGENTS.md@sha256:44307f46a7579048The line at the top of this page pins the label git:20261118.7e9cff8, 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_a42xivx4zy3ermjs)
0 badge image fetches in 30 days. What the badge shows.
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it: what changed in amd-agi/aklr/tests/AGENTS.md since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.
Got a copy of AGENTS.md from somewhere else? Ask it: where did my AGENTS.md come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.
Versions
The registry has recorded 2 versions of this file, all committed on Nov 18, 2026.
Watch this file (sign in, one email per new version)
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261118.7e9cff8 latest | 2026-11-18 | 7e9cff8 | 2,540 B | A | view · diff |
| git:20261118.5640084 | 2026-11-18 | 5640084 | 2,429 B | A | view |
Installed this file, say at AGENTS.md? Drop it here to learn which saved version you have and what changed since. Your browser works out its SHA-256 fingerprint and sends only that; the file itself never leaves your computer.
Or paste its contents
Your agent can run this same check on the agent markdown files you have installed, up to 50 in one ask. Add the registry once:
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it to check the files you have installed. No key and no account.
From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies
In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies
No sha256sum on your machine? shasum -a 256 prints the same lines.
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (2540 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
amd-agi/aklr · 15 stars · license MIT · pushed 2026-11-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_a42xivx4zy3ermjs GET https://markdownregistry.com/api/v1/resolve?ref=amd-agi/aklr/tests/AGENTS.md GET https://markdownregistry.com/api/v1/blob/44307f46a75790484bc42e5de5cb3ed92ad1bb9941bab1cee666c70f81d54645
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.