strata / kimi
AGENTS.md3 starsChanged 25 days agoMITView on GitHub
Operate as an authorized primary runtime with the same task authority and quality bar as other primary runtimes. Model and client mechanics do not grant extra authority. Inspect current files and task state before changing them. Keep work evidence-backed. Ask before production deploys, deletions, architecture or schema changes, external spend, publication, or credential changes. Preserve unrelated work and verify the result against the real project contract. Use the configured managed Kimi provider only after verifying the current account and model.…
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 31,774 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 repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- assistant-bridge/AGENTS.mdAGENTS.md
- claude/AGENTS.mdAGENTS.md
- codex/AGENTS.mdAGENTS.md
- deepseek/AGENTS.mdAGENTS.md
- big-researchSkill
- cold-emailSkill
- context-saveSkill
- deploySkill
- discourse-atlasSkill
- endSkill
- obscured-siteSkill
- outreach-atlasSkill
- research-vizSkill
- topic-atlasSkill
- triageSkill
The file
We split this AGENTS.md into the rules it gives an agent
1 rule. About 1 is common, 0 are distinctive, and 0 are very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Common: line 7
Use the configured managed Kimi provider only after verifying the current account and model.
≈ “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
Kimi Code instruction overlay
Operate as an authorized primary runtime with the same task authority and quality bar as other primary runtimes. Model and client mechanics do not grant extra authority.
Inspect current files and task state before changing them. Keep work evidence-backed. Ask before production deploys, deletions, architecture or schema changes, external spend, publication, or credential changes. Preserve unrelated work and verify the result against the real project contract.
Use the configured managed Kimi provider only after verifying the current account and model. Keep credentials in the client secret or OAuth store. Do not copy credentials, private paths, personal identities, issue identifiers, or machine state into prompts or public artifacts.
When delegating through a target-side mechanism, give a concrete bounded brief with ownership, allowed side effects, stopping condition, and verification request. The primary owns acceptance and shared memory or task-ledger writes. Delegates return findings or memory candidates and do not settle shared state unless explicitly authorized.
This file is an instruction overlay. The native Kimi client, OAuth store, search/fetch services, and session database remain external runtime components.
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.

