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/darwin/supex/claude-mdgit clone --depth 1 https://github.com/darwin/supexWhat 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 | $0.00706 | $0.00706 |
| Opus 5 | $0.00353 | $0.00353 |
| Sonnet 5 | $0.00141 | $0.00141 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
supex CLAUDE.md scanned grade A with 0 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 3d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code when working on this repository.
Branch Strategy
main: Stable releases only. Do not commit directly.dev: Active development. All work here.
Guidelines
- NEVER bump version numbers unless explicitly asked
- NEVER commit changes unless explicitly asked
- NEVER read git-ignored files unless explicitly asked
- NEVER use emojis in documentation
- Use
git ls-tree -r HEADto find project files - Use portable shebangs -
#!/usr/bin/env bash,#!/usr/bin/env python3, etc.
Project Structure
supex/
├── driver/ # Python MCP driver + CLI
│ └── src/supex_driver/
│ ├── cli/ # CLI commands
│ ├── connection/ # SketchUp socket connection
│ └── mcp/ # MCP server
├── runtime/ # Ruby SketchUp extension
│ └── src/
│ ├── supex_runtime.rb # Extension entry point
│ └── supex_runtime/ # Extension modules
├── docs/ # Documentation
│ └── agents/ # Agent prompts (symlinked as supex-docs/)
├── docgen/ # SketchUp API doc generator
├── stdlib/ # Standard library (Ruby helpers)
├── scripts/ # Development scripts
└── examples/ # Example projects (orphan branches)
Architecture
MCP-based platform connecting AI agents to SketchUp:
- Python MCP Driver (
driver/) - FastMCP server exposing tools to AI - Ruby Runtime (
runtime/) - SketchUp extension executing commands - Socket Communication - TCP on localhost:9876 (default)
Development Commands
# Launch SketchUp with extension
./scripts/launch-sketchup.sh
# CLI commands
./supex status
./supex info
./supex reload
# Run tests
cd driver && uv run pytest tests/
# Build production .rbz
cd runtime && bundle exec rake build
Key Files
Driver (Python):
driver/src/supex_driver/mcp/server.py- MCP server and toolsdriver/src/supex_driver/connection/connection.py- Socket connectiondriver/src/supex_driver/cli/main.py- CLI implementation
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.
- 3d ago First seen · 88 lines · 706 tokens per session scan A 6708980c7fa2
supex CLAUDE.md is an instructions file published in the GitHub repository darwin/supex (44 stars, last pushed 1mo ago), licensed MIT. It adds 706 tokens to every session, about $0.0035 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
ii-agent AGENTS.md
Instructions for Intelligent-Internet/ii-agent, covering ii-agent contributor guide, quick start, repository map, mandatory rules and architecture.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
nimbalyst AGENTS.md
AGENTS.md instructions for nimbalyst/nimbalyst: At the beginning of every AI session, read the root CLAUDE.md and any applicable package-level CLAUDE.md before taking actions.
sortie copilot-instructions.md
Instructions for sortie-ai/sortie, covering sortie coding & review standards, 1. layered imports (downward only; violation is critical), 2. concurrency safety, 3. workspace path safety (critical: security boundary) and 4. persistence (sqlite).
GENesis-AGI AGENTS.md
AGENTS.md instructions for WingedGuardian/GENesis-AGI, covering agent instructions, code review mandate (adversarial), gitnexus — code intelligence (advisory), genesis capability surface and skills.