my-ai-tools / wiki
AGENTS.md127 starsChanged 26 days agoMITView on GitHub
This wiki is a persistent, compounding knowledge base for my-ai-tools — a monorepo for managing configuration across 14+ AI coding assistants (Claude Code, OpenCode, Amp, Codex, Gemini CLI, Pi, Cursor, etc.). The wiki is a set of markdown files maintained by the LLM. Follow these rules: This wiki is part of the my-ai-tools repo. See the root AGENTS.md for project-wide conventions (bash scripting, git safety, testing with bats).
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 repository38 other files it gives its agents.
- AGENTS.mdAGENTS.md
- wiki/CLAUDE.mdCLAUDE.md
- accountable-engineeringSkill
- adrSkill
- babysit-prSkill
- blindspot-passSkill
- capability-experimentsSkill
- codemapSkill
- code-quality-reviewSkill
- code-reviewSkill
- commit-atomicSkill
- context-discoverySkill
- diagnosing-bugsSkill
- doc-searchSkill
- docs-updateSkill
- draft-pull-requestSkill
- git-contextSkill
- handoffsSkill
- implementation-loggerSkill
- implement-specSkill
- llm-wikiSkill
- orchestrating-fusionSkill
- pickupSkill
- plannotator-setup-goalSkill
- portless-localSkill
- prdSkill
- pr-reviewSkill
- prSkill
- qmd-knowledgeSkill
- quiz-meSkill
- ralphSkill
- retroSkill
- security-auditSkill
- slopSkill
- spec-interviewSkill
- tddSkill
- tmuxSkill
- visual-prSkill
The file
We split this AGENTS.md into the rules it gives an agent
5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 21
Immutable sources: Never modify files in raw/.
- Distinctive: line 22
One ingest at a time: Read, summarize, ask for emphasis, then create/update 5–15 pages.
- Very specific: line 23
Cross-references: Use [[Page Name]] wiki links.
- Very specific: line 24
Contradictions: Add > [!NOTE] Contradiction blocks when new sources conflict with existing content.
- Very specific: line 26
Keep index current: Every new or changed page must appear in wiki/index.md.
≈ “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
LLM Wiki — Agent Instructions
What This Is
This wiki is a persistent, compounding knowledge base for my-ai-tools — a monorepo for managing configuration across 14+ AI coding assistants (Claude Code, OpenCode, Amp, Codex, Gemini CLI, Pi, Cursor, etc.).
How to Work With This Wiki
The wiki is a set of markdown files maintained by the LLM. Follow these rules:
Operations
/llm-wiki init— Initialize the wiki structure/llm-wiki ingest <source>— Integrate a new source file/llm-wiki query <question>— Answer using wiki knowledge/llm-wiki lint— Health-check for contradictions, orphans, gaps/llm-wiki status— Show wiki summary
Conventions
- Immutable sources: Never modify files in
raw/. Sources are append-only. - One ingest at a time: Read, summarize, ask for emphasis, then create/update 5–15 pages.
- Cross-references: Use
[[Page Name]]wiki links. Link on first mention per page. - Contradictions: Add
> [!NOTE] Contradictionblocks when new sources conflict with existing content. - Log every operation: Append to
wiki/log.mdafter every ingest, query (if filed), or lint. - Keep index current: Every new or changed page must appear in
wiki/index.md. - File good answers: Valuable query results should become wiki pages.
Project Context
This wiki is part of the my-ai-tools repo. See the root AGENTS.md for project-wide conventions (bash scripting, git safety, testing with bats).
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.