Package Exports
This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (@tanagram/cli) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.
Readme
Tanagram
A lightweight Go CLI that enforces policies from AGENTS.md files on your local git changes.
Quick Start
Run tanagram before committing to catch policy violations locally:
$ tanagram
✗ Found 1 policy violation(s):
webui/src/Button.tsx:42 - [No hardcoded colors] Don't use hard-coded color values; use theme colors instead
> background: "#FF5733"Installation
Via npm (Recommended)
npm install -g @tanagram/cli
tanagram --helpRequirements:
- Node.js >= 14.0.0
- Go >= 1.21 (for building the binary during installation)
- Anthropic API Key (required for LLM-based policy extraction)
The CLI is written in Go but distributed via npm for easier installation and version management.
API Key Setup
Tanagram uses Claude AI (via Anthropic API) to extract policies from your instruction files. You need to bring your own API key:
# Set your Anthropic API key
export ANTHROPIC_API_KEY="sk-ant-..."
# Or add to your shell profile (~/.bashrc, ~/.zshrc, etc.)
echo 'export ANTHROPIC_API_KEY="sk-ant-..."' >> ~/.zshrcGet an API key:
- Sign up at https://console.anthropic.com
- Create an API key in the dashboard
- Set the
ANTHROPIC_API_KEYenvironment variable
Local Development
cd cli
npm install # Builds the Go binary
./bin/tanagramInstall Locally for Testing
Install globally from the local directory to test as if it were published:
cd /Users/molinar/tanagram/cli
npm install -g .Then run from anywhere:
tanagramUsage
# Check all changes (unstaged + staged) - automatically syncs if policies changed
tanagram
# or explicitly:
tanagram run
# Manually sync instruction files to cache
tanagram sync
# View all cached policies
tanagram list
# Show help
tanagram helpSmart Caching: Policies are cached and automatically resynced when instruction files change (detected via MD5 hash).
Commands
run(default) - Check git changes against policies with auto-syncsync- Manually sync all instruction files to cachelist- View all cached policies (shows enforceable vs unenforceable)help- Show usage information
How It Works
- Finds instruction files - Searches for
AGENTS.md,POLICIES.mdin your git repository - Checks cache - Loads cached policies and MD5 hashes from
.tanagram/ - Auto-syncs - Detects file changes via MD5 and automatically resyncs if needed
- LLM extraction - Uses Claude AI to extract ALL policies from instruction files
- Gets git diff - Analyzes all your changes (unstaged + staged)
- LLM detection - Checks violations using intelligent semantic analysis
- Reports results - Terminal output with detailed reasoning for each violation
Cache Location
Policies are cached in .tanagram/cache.gob at your git repository root. Add this to your .gitignore:
.tanagram/Fully LLM-Based Architecture
Tanagram uses 100% LLM-powered policy extraction and enforcement:
Extraction Phase
Claude AI extracts ALL policies from instruction files:
- No classification needed (no MUST_NOT_USE, MUST_USE, etc.)
- No regex pattern generation
- Simple: Just extract policy names and descriptions
- Fast: Simpler prompts = faster responses
Detection Phase
Claude AI analyzes code changes against all policies:
- Semantic understanding - Not just pattern matching
- Context-aware - Understands code intent and structure
- Language-agnostic - Works with any programming language
- Detailed reasoning - Explains why code violates each policy
What Can Be Enforced
Everything! Because the LLM reads and understands code like a human:
Simple patterns:
- "Don't use hard-coded colors" → Detects
#FF5733,rgb(), etc. - "Use ruff format, not black" → Detects
blackusage - "Always use === instead of ==" → Detects
==operators
Complex guidelines:
- "Break down code into modular functions" → Analyzes function length and complexity
- "Don't deeply layer code" → Detects excessive nesting
- "Ensure no code smells" → Identifies common anti-patterns
- "Use structured logging with request IDs" → Checks logging patterns
- "Prefer async/await for I/O" → Understands async patterns
Language-specific idioms:
- Knows Go uses PascalCase for exports (not Python's snake_case)
- Won't flag Go code for missing Python type hints
- Understands JavaScript !== Python !== Go
Exit Codes
0- No violations found1- Violations found (fails CI/CD if integrated)
Example
Create an AGENTS.md in your repo with policies:
# Development Policies
- Don't use hard-coded color values; use theme colors instead
- Use ruff format for Python formatting, not black
- Always use async/await for database operationsThen run tanagram to enforce them locally!
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Development Setup
# Clone the repository
git clone https://github.com/tanagram/cli.git
cd cli
# Install dependencies and build
npm install
# Run tests
npm test
# Build manually
go build -o bin/tanagram .Publishing to npm
To publish a new version:
# Update version in package.json
npm version patch # or minor, or major
# Publish to npm
npm publish --access public
# Create git tag
git tag v$(node -p "require('./package.json').version")
git push origin --tagsLicense
MIT