langgraph-harness
AGENTS.md32 starsChanged 25 days agoMITView on GitHub
As you work, maintain an AI_NOTICE.md file in the repo root that records: If the user asks you to commit: include AI_NOTICE.md in the commit alongside the code changes. If the user asks you to create an MR: use the content of AI_NOTICE.md to fill out the MR description (see below), then delete the file and amend or follow up with a cleanup commit before pushing. AI_NOTICE.md is intentionally a dead man's switch. If a human reviewed the changes, they…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository8 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- bump-npm-depsSkill
- create-github-issueSkill
- create-gitlab-taskSkill
- debug-production-runSkill
- sync-architectureSkill
- update-changelogSkill
- update-server-depsSkill
The file
We split this AGENTS.md into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
If the user asks you to create an MR: use the content of AI_NOTICE.md to fill out the MR description (see below), then delete the file and …
- Very specific: line 19
Before creating a merge request, read file .gitlab/merge_request_templates/ai_disclosure.md and include template's content in the MR …
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Agent Instructions
Implementing Features and Bug Fixes
As you work, maintain an AI_NOTICE.md file in the repo root that records:
- What the user asked you to do.
- How much context or direction they gave you.
- How the work evolved — did the user review, correct, or iterate with you, or was this largely autonomous?
If the user asks you to commit: include AI_NOTICE.md in the commit alongside the code changes.
If the user asks you to create an MR: use the content of AI_NOTICE.md to fill out the MR description (see below), then delete the file and amend or follow up with a cleanup commit before pushing.
AI_NOTICE.md is intentionally a dead man's switch. If a human reviewed the changes, they would remove it. Its presence in a commit or MR signals that the changes were not reviewed before submission.
Merge Requests
Before creating a merge request, read file .gitlab/merge_request_templates/ai_disclosure.md and include template's content in the MR description exactly as specified.
The ai_disclosure.md template is mandatory. Check the box that accurately reflects your level of involvement, and use the content of AI_NOTICE.md verbatim for the agent context paragraph. The goal is genuine insight into how the change was made — not a boilerplate disclaimer.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.