AGENTS.md@plugins/rootloom/skills/setup-rootloomA
AGENTS.md@plugins/rootloom/skills/setup-rootloom from qingye-lab/rootloom is an AGENTS.md file: the standing instructions coding agents read in that repo.
mdr add qingye-lab/rootloom/plugins/rootloom/skills/setup-rootloom/AGENTS.md@git:20260810.c780041Pins git:20260810.c780041 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 14 of 14 checks passed
- Kind
- AGENTS.md file
- Repository
- qingye-lab/rootloom
- Path
plugins/rootloom/skills/setup-rootloom/AGENTS.md- Versions recorded
- 2
- Latest version
- git:20260810.c780041, committed Aug 10, 2026
- First version recorded
- Jul 16, 2026
- Size
- 772 bytes
- Repository stars
- 11
- 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
# Setup guidance - `scripts/setup_rootloom.py` owns Codex-home writes and capability-to-artifact mapping; keep it plan-first, conflict-refusing, lock-serialized, backup-backed, hash-aware, mode-preserving on rollback, and atomic per file. Treat global `AGENTS.md` as a marker-bounded managed block, preserve all content outside it, and never turn malformed markers into whole-file replacement. - Public presets are only `skills-only`, `guidance`, and `personal`; `engineering` remains a hidden compatibility alias. - `autonomy` is the canonical optional authorization capability; accept legacy `command-safety` input without presenting it as deterministic safety. - Setup is the only supported writer for component policy and must always emit exact integer `version: 1`.
Read the whole file at its exact version.
How to install
mdr add qingye-lab/rootloom/plugins/rootloom/skills/setup-rootloom/AGENTS.md@sha256:3bd3e8923bd4f38fThe line at the top of this page pins the label git:20260810.c780041, 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_nqpjgky6crrrv7bq)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Jul 16, 2026 and Aug 10, 2026, about one every 26 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260810.c780041 latest | 2026-08-10 | c780041 | 772 B | A | view · diff |
| git:20260716.a78ef59 | 2026-07-16 | a78ef59 | 617 B | A | view |
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (772 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
qingye-lab/rootloom · 11 stars · license MIT · pushed 2026-09-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_nqpjgky6crrrv7bq GET https://markdownregistry.com/api/v1/resolve?ref=qingye-lab/rootloom/plugins/rootloom/skills/setup-rootloom/AGENTS.md GET https://markdownregistry.com/api/v1/blob/3bd3e8923bd4f38fca2c09b9e62de08145be5ca63c802ce65b2c63a0560ce789
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.