AGENTS.mdA
AGENTS.md from leeguooooo/chatgpt-use is an AGENTS.md file: the standing instructions coding agents read in that repo.
mdr add leeguooooo/chatgpt-use/AGENTS.md@git:20260910.b54f840Pins git:20260910.b54f840 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 14 of 14 checks passed
- Kind
- AGENTS.md file
- Repository
- leeguooooo/chatgpt-use
- Path
AGENTS.md- Versions recorded
- 1
- Latest version
- git:20260910.b54f840, committed Sep 10, 2026
- Size
- 1,225 bytes
- Repository stars
- 57
- 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
# Agent rules for chatgpt-use ## Never test against the live ChatGPT Do **not** run anything that reaches the real chatgpt.com to verify a change. That means: - live `chatgpt-use ask / run / serve / work / resume / cancel` runs; - probe scripts; - `chrome-use site chatgpt/*` calls; - opening chatgpt.com under throwaway `--session` names. It drives the user's own signed-in account, and chatgpt.com throttles that account by **request count**. A full page load is about 45 backend requests. One afternoon of scripted live checks (roughly 23 full loads, mostly through fresh session names) tripped "Too many requests" on the account the user works in. Verify offline instead: - `cargo test`, which is fully offline and never calls chrome-use; - pure functions for anything the browser decides (see `judge_record`, `classify`, `receipt::live_state`, `structured::evaluate`), tested with fixtures. If something truly can only be confirmed live, say so and leave it marked unverified. Never run it yourself. ## Build …
Read the whole file at its exact version.
How to install
mdr add leeguooooo/chatgpt-use/AGENTS.md@sha256:d3b173a004d503abThe line at the top of this page pins the label git:20260910.b54f840, 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_5nukc7dg3fghl4f5)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 10, 2026.
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (1225 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
leeguooooo/chatgpt-use · 57 stars · license MIT · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_5nukc7dg3fghl4f5 GET https://markdownregistry.com/api/v1/resolve?ref=leeguooooo/chatgpt-use/AGENTS.md GET https://markdownregistry.com/api/v1/blob/d3b173a004d503aba277e1a33e9534409a6558673754b841cdea1685350d1f76
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 leeguooooo/chatgpt-use
Every file in leeguooooo/chatgpt-use