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/algorithmiq/monoprop/agents-mdgit clone --depth 1 https://github.com/Algorithmiq/monopropWhat 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 | $0.03468 | $0.03468 |
| Opus 5 | $0.01734 | $0.01734 |
| Sonnet 5 | $0.00694 | $0.00694 |
| Haiku 4.5 | $0.00347 | $0.00347 |
Grade C, and why
monoprop AGENTS.md scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Use `rm -rf build` to clear environment-specific builds How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions for monoprop
monoprop is a high-performance C++/Python hybrid library implementing Majorana and Pauli propagation. The project combines modern C++23 with Python bindings via nanobind.
Repository rules
- C++23: All C++ code must use C++23 features and idioms.
- Auto style: Use
clang-formatwith the provided.clang-formatfile - Python code must pass lints as defined in pre-commit hooks.
- We use conventional commits with syntax:
<type>(<optional scope>): <gitmoji> <description>:- Commit body and footers are optional.
- Breaking changes should have
!in the commit message. <type>can only be one of:feat: new feature, preserving the API. This corresponds to a minor version bump.fix: bug fix. This corresponds to a patch version bump.docs: changes to the documentation. No functional changes.style: formatting, i.e. runningblack. No functional changes.refactor: refactoring production code, i.e. improving class structure. No functional changes.test: adding/refactoring tests, i.e. improving code coverage. No functional changes.chore: "boring" tasks, i.e. updating dependency pins inpyproject.toml. No functional changes.
- If you make a commit, add a trailer:
Assisted-by: <harness>:<model>, where<harness>is the current agent harness (like ClaudeCode), and<model>is the AI model (like claude-opus-4.8). You don't need to add a coauthored-by when you have this. - PR titles must adhere to the same conventional commits format. PR text should follow the PR template in the
.githubfolder. - Prefix PR descriptions and comments on PRs with the line ":robot: AI text below :robot:" to indicate you are an agent speaking on a user's behalf.
- Python docstrings use Google style, and are rendered into the docs site by
just gen-api— keep them accurate. - In prose docs (
docs/content/docs/**.mdx) and Python docstrings, link to API symbols with the mkdocstrings-style[Symbol][]reference (or[Display][fully.qualified.path]) — never hard-code/api/...URLs. Do not backtick the name in the[Symbol][]form. Seedocs/content/docs/documenting.mdx. - C++ comments: bare
//for one-line comments,/* */for block comments. - Add Doxygen Qt-style documentation on all declarations in header files. Put documentation after members in enums, structs, classes.
- Comments state what the code cannot: invariants, ordering and lifetime contracts, sign and bit conventions, and why an obvious alternative was rejected. Do not restate the code, narrate history (git has it), or repeat a fact that already has a home elsewhere.
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 · 198 lines · 3,468 tokens per session scan C f944242c522a
monoprop AGENTS.md is an instructions file published in the GitHub repository Algorithmiq/monoprop (43 stars, last pushed 3d ago), licensed Apache-2.0. It adds 3,468 tokens to every session, about $0.0173 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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.
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).
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.
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.