my-llm-kit
AGENTS.md3 starsChanged 43 days agoMITView on GitHub
This repository distributes agent instructions, skills and optional integrations. The shared policy lives in instructions/AGENTS.md; the README installation prompt installs that file as the global policy. This file contains only repository-specific constraints. - Preserve unrelated worktree changes. Verify distribution using temporary user and consumer directories; do not change the real machine installation as a test. - Keep installation instructions in README.md and the default install small. Optional integrations require a user selection; already installed user skills and guards remain untouched.…
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 repository9 other files it gives its agents.
- instructions/AGENTS.mdAGENTS.md
- agent-graphSkill
- computer-useSkill
- frontend-visual-validationSkill
- remove-ai-marksSkill
- researchSkill
- rule-curatorSkill
- scrapingdogSkill
- stagehand-browserSkill
The file
We split this AGENTS.md into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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
- Distinctive: line 10
Keep installation instructions in README.md and the default install small.
- Distinctive: line 16
Keep journal generation, task ownership, check provenance and resource cleanup intact when changing graph execution.
- Distinctive: line 19
Do not add GitHub Actions, test suites, test fixtures or development test/lint dependencies.
- Distinctive: line 23
Keep installation outcomes independent of the shell and harness.
≈ “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
my-llm-kit development
This repository distributes agent instructions, skills and optional integrations.
The shared policy lives in instructions/AGENTS.md; the README installation
prompt installs that file as the global policy. This file contains only
repository-specific constraints.
- Preserve unrelated worktree changes. Verify distribution using temporary user and consumer directories; do not change the real machine installation as a test.
- Keep installation instructions in README.md and the default install small. Optional integrations require a user selection; already installed user skills and guards remain untouched. Do not add machine setup scripts or a second installation catalog.
- Resolve installed scripts from their skill directory and pass the consumer
project separately. Do not assume a consumer has
skills/in its checkout. - Keep journal generation, task ownership, check provenance and resource cleanup intact when changing graph execution. Scope changes amend the existing task contract; do not add another ledger or scheduler.
- Do not add GitHub Actions, test suites, test fixtures or development test/lint dependencies. Verify changes by inspecting the affected files, links and necessary runtime behavior. Shared instructions about tests govern consumer projects, not this collection.
- Keep installation outcomes independent of the shell and harness. Report untested operating systems or hosts as unverified, not supported by inference.
- Skill edits use
skill-creator; preserve licenses, reference links and implicit invocation policy. Keep domain-specific detail out of shared instructions. - Commits use conventional format without agent names or co-author trailers.
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.