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/randomm/oo/agents-mdgit clone --depth 1 https://github.com/randomm/ooWhat 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 | $0.01368 | $0.01368 |
| Opus 5 | $0.00684 | $0.00684 |
| Sonnet 5 | $0.00274 | $0.00274 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade A, and why
oo 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — oo Project
Agent guidelines for the oo codebase (Rust, Edition 2024).
1. Context7 Protocol
Before writing any Rust code, resolve current documentation via Context7:
context7_resolve-library-id → context7_query-docs
Use this for crate APIs (tokio, clap, rusqlite, thiserror, assert_cmd, etc.).
Training data may be outdated — Context7 has authoritative current docs.
2. Minimalist Engineering Philosophy
Every line of code is a liability. Before creating anything:
- LESS IS MORE: Question necessity before creation
- Challenge Everything: Ask "Is this truly needed?" before implementing
- Minimal Viable Solution: Build the simplest thing that fully solves the problem
- No Speculative Features: Don't build for "future needs" - solve today's problem
- Prefer Existing: Reuse existing code/tools before creating new ones
- One Purpose Per Component: Each function/module should do one thing well
Pre-Creation Challenge (MANDATORY)
Before creating ANY code, ask:
- Is this explicitly required by the GitHub issue?
- Can existing code/tools solve this instead?
- What's the SIMPLEST way to meet the requirement?
- Will removing this break core functionality?
- Am I building for hypothetical future needs?
If you cannot justify the necessity, DO NOT CREATE IT.
3. Pre-Push Quality Gates
All checks must pass locally before any push. CI is for verification, not discovery.
cargo fmt --check # formatting
cargo clippy -- -D warnings # lint (warnings are errors)
cargo test # all tests pass
cargo tarpaulin --fail-under 70 # coverage gate (70% interim, 80% target after VCR cassettes)
cargo build --release # release build succeeds
Fix failures locally. Never push to "see if CI catches anything."
4. Testing Standards
- TDD preferred — write tests before implementation
- 80% line coverage minimum for new code — enforced via
cargo tarpaulin - Unit tests in-module (
#[cfg(test)]) for pure logic - Integration tests in
tests/for CLI behaviour — useassert_cmd - Integration tests are the primary coverage driver — they test real CLI invocations
- Every new pattern in
src/pattern/must have a corresponding test - Tests must provide real value — no trivial assertions like
assert!(true)orassert_eq!(1, 1) - Every test must exercise a real code path and assert meaningful behaviour
- Network-dependent tests must be marked
#[ignore]with a comment explaining why - ~197 tests currently; do not reduce this count
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 · 145 lines · 1,368 tokens per session scan A 3ebe48ecc39b
oo AGENTS.md is an instructions file published in the GitHub repository randomm/oo (21 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 1,368 tokens to every session, about $0.0068 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
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.