aiframework
CLAUDE.md0 starsChanged 7 months agoMITView on GitHub
Make Claude Code understand your project instantly. Stack: Rust. Most important files (by dependency rank): - rust/src/cli.rs - rust/src/indexer/mod.rs - rust/src/scanner/mod.rs - rust/src/generator/mod.rs - rust/src/generator/claude_md.rs - rust/src/config.rs - rust/src/ui.rs - rust/src/indexer/graph.rs - rust/src/validator/mod.rs - rust/src/mcp/mod.rs Generated by aiframework v2.0.0. Stack: Rust.
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- aif-analyzeSkill
- aif-enhanceSkill
- aif-evolveSkill
- aif-feedbackSkill
- aif-ingestSkill
- aif-learnSkill
- aif-pulseSkill
- aiframework-learnSkill
- aiframework-reviewSkill
- aiframework-shipSkill
- aif-readySkill
- aif-researchSkill
- aif-reviewSkill
- aif-shipSkill
- aif-statusSkill
- retroSkill
- sheal-askSkill
- sheal-checkSkill
- sheal-driftSkill
- sheal-retroSkill
The file
We split this CLAUDE.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 60
INV-2: No secrets in source code
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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
CLAUDE.md — aiframework
Make Claude Code understand your project instantly. Stack: Rust.
| You need to... | Read |
| Understand this repo | This file |
| See architecture | docs/reference/architecture.md |
| Check workflow rules | .claude/rules/workflow.md |
Commands
# Build
cd rust && cargo build --release
# Lint
cd rust && cargo clippy
# Test
cd rust && cargo test
# Run
cd rust && cargo run -- run --target /path/to/repoArchitecture
- Stack: Rust (single binary, 8.9 MB, zero runtime deps)
- Archetype: cli-tool (active, complex)
Key Locations
- CLI:
rust/src/cli.rs - Scanners:
rust/src/scanner/(13 scanners) - Indexer:
rust/src/indexer/(13 language parsers, 8 tree-sitter) - Generators:
rust/src/generator/(14 generators) - Validators:
rust/src/validator/mod.rs(5 checks) - MCP Server:
rust/src/mcp/mod.rs - Config/Tiers:
rust/src/config.rs - Telemetry:
rust/src/telemetry.rs - UI:
rust/src/ui.rs - Language Registry:
rust/data/languages.json
Most important files (by dependency rank):
rust/src/cli.rsrust/src/indexer/mod.rsrust/src/scanner/mod.rsrust/src/generator/mod.rsrust/src/generator/claude_md.rsrust/src/config.rsrust/src/ui.rsrust/src/indexer/graph.rsrust/src/validator/mod.rsrust/src/mcp/mod.rs
Invariants
- INV-1: LLM trust boundary — validate all AI output
- INV-2: No secrets in source code
Gotchas
- Tree-sitter parsers are NOT thread-safe — create one per rayon thread
- Generators never overwrite user-created files (check
write_if_missing_or_generated) - Tier system gates generators: Lean < Standard < Full < Enterprise
rust/data/languages.jsonis embedded at compile time viainclude_str!- Manifest field names must match bash version for backward compatibility (e.g.,
shortalias)
Makefile
make build
make install
make uninstall
make lint
make test
make check
make distKey State
- Source files: 67 Rust files
- Tests: 42 (cargo test)
- Binary: 8.9 MB (release, stripped, LTO)
Generated by aiframework v2.0.0. Stack: Rust.
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.

