Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/kasarlabs/cairo-coder/claude-mdgit clone --depth 1 https://github.com/KasarLabs/cairo-coderWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01514 | $0.01514 |
| Opus 5 | $0.00757 | $0.00757 |
| Sonnet 5 | $0.00303 | $0.00303 |
| Haiku 4.5 | $0.00151 | $0.00151 |
Grade C, and why
cairo-coder CLAUDE.md scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -LsSf https://astral.sh/uv/install.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -LsSf https://astral.sh/uv/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Agent instructions for working with Cairo Coder.
Project Overview
Cairo Coder is a Cairo language code generation service using RAG (Retrieval-Augmented Generation) with DSPy.
Stack: Python/FastAPI backend, TypeScript/Bun ingester, PostgreSQL/pgvector database.
Essential Commands
Python Backend (from python/ directory)
# Setup
curl -LsSf https://astral.sh/uv/install.sh | sh
uv sync
# Run server
uv run cairo-coder # Start FastAPI server
uv run cairo-coder --dev # Development mode with auto-reload
# Testing
uv run pytest # Run all tests
uv run pytest -k "test_name" # Run specific test
uv run pytest --cov=src/cairo_coder # With coverage
# Linting & Type Checking
trunk check --fix # Lint and auto-fix
uv run ty check # Type checking
Ingester (from ingesters/ directory)
# Setup
bun install
# Run ingestion
bun run generate-embeddings # Interactive
bun run generate-embeddings:yes # Non-interactive (CI/CD)
# Testing
bun test
Docker
# From root directory
docker compose up postgres backend # Start services
docker compose up postgres ingester # Run ingestion
Key File Locations
| Component | Location |
|---|---|
| RAG Pipeline | python/src/cairo_coder/dspy/ |
| Agent Registry | python/src/cairo_coder/agents/registry.py |
| API Server | python/src/cairo_coder/server/app.py |
| Core Types | python/src/cairo_coder/core/types.py |
| Ingesters | ingesters/src/ingesters/ |
| Ingester Types | ingesters/src/types/index.ts |
| Optimized Programs | python/optimizers/results/ |
Development Guidelines
Python
- Use
uvfor all dependency management (not pip/poetry) - Follow DSPy patterns: Signatures -> Modules -> Programs
- Type hints required (enforced by mypy)
- Use structlog for logging:
get_logger(__name__) - Async/await for I/O operations
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 196 lines · 1,514 tokens per session scan C 5ab95a998f77
cairo-coder CLAUDE.md is an instructions file published in the GitHub repository KasarLabs/cairo-coder (40 stars, last pushed 2mo ago), licensed MIT. It adds 1,514 tokens to every session, about $0.0076 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.