ai-mind-map / templates
AGENTS.md3 starsChanged 25 days agoMITView on GitHub
Use native search for exact strings, known paths, and small files. Use the local graph for repeated symbols, callers, routes, and architecture questions. When alignment is unknown, check mindmap_status once and set mindmap_set_project(projectPath: "<absolute path>") if needed. Refresh after external changes. Size/mtime checks can miss preserved-metadata edits. Verify consequential claims against source and tests. AST deltas are not behavioral verification. Graph edges can be incomplete or heuristic; an empty result does not prove absence. If MCP is unavailable, use ai-mind-map…
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 repository11 other files it gives its agents.
- .agents/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- templates/CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- ai-mind-mapSkill
- codebase-security-auditSkill
- git-diffSkill
- testsprite-onboardSkill
- testsprite-verifySkill
- ai-mind-mapSkill
- git-diffSkill
The file
We split this AGENTS.md into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 3
Use native search for exact strings, known paths, and small files.
- Very specific: line 5
When alignment is unknown, check mindmap_status once and set mindmap_set_project(projectPath: "<absolute path>") if needed.
- Very specific: line 7
Search: mindmap_smart_search(query: "...", limit: 5).
- Very specific: line 16
If MCP is unavailable, use ai-mind-map search, trace, routes, or native tools.
≈ “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
AI Mind Map MCP
Use native search for exact strings, known paths, and small files. Use the local graph for repeated symbols, callers, routes, and architecture questions.
When alignment is unknown, check mindmap_status once and set mindmap_set_project(projectPath: "<absolute path>") if needed.
- Search:
mindmap_smart_search(query: "...", limit: 5). Signatures are the default; request code or callers only when needed. - Relationships:
mindmap_explain(symbol: "...", filePath: "...", depth: 1). - Routes:
mindmap_route_map(prefix: "/api", limit: 20). Check truncation and unresolved coverage. - Exact Git comparisons:
ai-mind-map diff [base] [target]exports a local patch and viewer. Use--fetchfor a refreshed remote base. Read patch hunks into chat only when analysis is requested. - Source:
mindmap_file_skeleton(file: "...")for unfamiliar structure;mindmap_read_lines(filePath: "...", startLine: X, endLine: Y)for logic. Direct bounded reads are valid. - Memory:
mindmap_rememberfor durable facts;mindmap_recallfor prior knowledge.
Refresh after external changes. Size/mtime checks can miss preserved-metadata edits. Verify consequential claims against source and tests. AST deltas are not behavioral verification. Graph edges can be incomplete or heuristic; an empty result does not prove absence.
If MCP is unavailable, use ai-mind-map search, trace, routes, or native tools. Do not force extra graph calls when direct evidence is cheaper.
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.