agentleFS
Sign inStart free
cdeustcdeust/ai-architect-mcp-codebase/CLAUDE.md

ai-architect-mcp-codebase

CLAUDE.md7 starsChanged 3 months agoMITView on GitHub

Rust MCP server: parses repositories with tree-sitter, builds a code graph, answers structural queries. This file is deliberately short: the host harness (hooks, skills, agents) loads what it needs on demand. Everything that used to be here is in docs/agent-guidance.md (environment quirks, gates that fail CI but not local runs, etiquette). Read it before any non-trivial change. Exit 0 requires aggregate ≥0.85 and every language ≥0.75. - This clone is live-mounted as the installed plugin: never checkout, pull, stash, or…

The file

Create a free account to mount
Files
CLAUDE.md

ai-architect-mcp-codebase

Rust MCP server: parses repositories with tree-sitter, builds a code graph, answers structural queries.

This file is deliberately short: the host harness (hooks, skills, agents) loads what it needs on demand. Everything that used to be here is in docs/agent-guidance.md (environment quirks, gates that fail CI but not local runs, etiquette). Read it before any non-trivial change.

Commands

cargo test --lib                                    # unit tests
cargo test --test graph_accuracy                    # accuracy gate
cargo run --release -p bench-end-result --bin bench_end_result -- --all   # note the -p

Exit 0 requires aggregate ≥0.85 and every language ≥0.75.

Non-negotiables

  • This clone is live-mounted as the installed plugin: never checkout, pull, stash, or build a different branch in it — the running MCP server dies. Work in a worktree: git worktree add .claude/worktrees/<topic> -b <branch> origin/main.
  • bin/ensure-binary.sh pins the SHA-256 of Cargo.toml and .claude-plugin/plugin.json — update both together or CI fails.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free