Borrowing it
Nothing to install: this file belongs to darwin/supex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/darwin/supex/main/AGENTS.mdgit clone --depth 1 https://github.com/darwin/supexWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/darwin/supex/agents-md)<a href="https://agentmods.dev/instructions/darwin/supex/agents-md"><img src="https://agentmods.dev/badge/instructions/darwin/supex/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/darwin/supex/agents-md"><img src="https://agentmods.dev/badge/instructions/darwin/supex/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.02872 | $0.02872 |
| Opus 5 | $0.01436 | $0.01436 |
| Sonnet 5 | $0.00574 | $0.00574 |
| Haiku 4.5 | $0.00287 | $0.00287 |
Grade A, and why
supex AGENTS.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 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.
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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents (Claude, Codex, Gemini, ...) when working on this repository.
CLAUDE.md is a symlink to this file for Claude Code compatibility.
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
- NEVER include
vcad/vendor/*submodule pointer changes in regular commits — use thecommit-vendorskill instead. All vendored submodules track upstreammaindirectly (no local patches); a pointer must be an upstream commit, otherwise the repo becomes uncloneable. Changes a vendored crate needs go upstream as a PR, never into a patch branch. - Use
git ls-tree -r HEADto find project files - Use portable shebangs -
#!/usr/bin/env bash,#!/usr/bin/env python3, etc.
For AI Agents — Common Mistakes
# WRONG — git add includes vendor submodule pointer changes
git add -A && git commit -m "Add feature"
# CORRECT — exclude vendor, use commit-vendor skill for submodule changes
git add driver/ runtime/
git diff --cached --name-only | grep -v vcad/vendor/
# WRONG — debug build (SketchUp loads release binary)
cargo build --manifest-path vcad/sidecar/Cargo.toml
# CORRECT — always build release
cargo build --release --manifest-path vcad/sidecar/Cargo.toml
# WRONG — find/ls to discover project files (misses git-ignored state)
find . -name "*.rb"
# CORRECT — git ls-tree shows tracked files only
git ls-tree -r HEAD --name-only | grep '\.rb$'
Project Structure
supex/
├── .github/ # GitHub Actions workflows and Dependabot config
├── driver/ # Python MCP driver + CLI
│ └── src/supex_driver/
│ ├── cli/ # CLI commands
│ ├── connection/ # SketchUp socket connection
│ └── mcp/ # MCP server
├── runtime/ # Ruby SketchUp extension
│ ├── ide_stubs/ # Shims so IDEs resolve sketchup.rb / extensions.rb
│ └── src/
│ ├── supex_runtime.rb # Extension entry point
│ └── supex_runtime/ # Extension modules
├── stdlib/ # Standard library (Ruby helpers)
├── mock/ # Headless SketchUp API mock server (Ruby) for tests without SketchUp
├── vcad/ # VCAD integration
│ ├── sidecar/ # Rust VCAD evaluator (BRep pipeline)
│ ├── viewer/ # Standalone Tauri geometry viewer
│ └── vendor/ # Git submodules (vcad, loon, tang)
│ ├── vcad/ # BRep CAD kernel
│ ├── loon/ # Loon language
│ └── tang/ # Differentiable computing (autodiff for VCAD)
├── tests/ # E2E tests (pytest) and the Ruby snippets they execute
├── docs/ # Documentation
│ ├── agents/ # Agent prompts (user projects symlink guide/ as supex-guide/)
│ └── contracts/ # JSON schemas and example payloads for the wire protocol
├── devtools/ # Developer tools
│ ├── ci/ # Dockerfile for the GitHub Actions test image
│ ├── docgen/ # SketchUp API doc generator (+ sketchup-api-stubs submodule)
│ └── radar/ # Log aggregator / observability
├── assets/ # README posters and the prompts that generated them
├── scripts/ # Development scripts
├── examples/ # Example projects (orphan branches)
├── justfile # just recipes: sketchup, test, test-e2e, docs, lint, clear-rust-caches
├── supex, mcp, repl # Root wrappers: CLI, MCP server, REPL client
└── test, radar, vcad-sidecar # Root wrappers: test runner, radar TUI, VCAD sidecar
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 · 253 lines · 2,872 tokens per session scan A 2ae2d7a1e123
supex AGENTS.md is an instructions file published in the GitHub repository darwin/supex (45 stars, last pushed 2d ago), licensed MIT. It adds 2,872 tokens to every session, about $0.0144 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 2026-09-07.
Other instructions, from other repositories
agent-compass pr-workflow.instructions.md
Instructions for me-cedric/agent-compass: For PR creation, default base branch is develop. Assign the PR to yourself with --assignee @me. If reviewers are not specified, ask for at least one and list likely repo contributors. Use only labels that exist in gh label list.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
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).
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.