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/rustfs/cli/agents-mdgit clone --depth 1 https://github.com/rustfs/cliWhat 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 | $0.02685 | $0.02685 |
| Opus 5 | $0.01342 | $0.01342 |
| Sonnet 5 | $0.00537 | $0.00537 |
| Haiku 4.5 | $0.00268 | $0.00268 |
Grade A, and why
cli 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 yesterday.
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 — 399 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - AI Development Guidelines
This document defines the standards and constraints that AI assistants must follow when developing the rc project.
Language Requirements
Important: All content must be in English, except for conversations with AI assistants which may use Chinese:
- Code comments
- Commit messages
- PR titles and descriptions
- Documentation in code
- Error messages in code
- Log messages
- Variable and function names
First-Principles Reasoning
Use first-principles thinking. Do not assume the user always has a fully formed understanding of what they want or how to achieve it. Start from the underlying need and problem, and proceed carefully. If the motivation or goal is unclear, stop and discuss it with the user. If the goal is clear but the proposed path is not the shortest or most effective, say so and recommend a better approach.
Workflow
0. Branch Base Policy
- For any code change task, always base work on the latest
origin/main. - Before implementing code changes, run
git fetch originand ensure your working branch is created from or rebased ontoorigin/main. - Exception: if the task explicitly asks to fix or update a specific PR branch, continue on that PR branch instead of rebasing to
origin/mainunless explicitly requested.
1. Before Starting
- Understand the task goals and acceptance criteria
- Identify related modules and existing tests
2. Before Modifying
- Check if the target file is a protected file
- If it's a protected file, follow the Breaking Change process
- Read related existing code to understand patterns and conventions
3. During Implementation
- Write tests first (red)
- Implement minimum code to pass tests (green)
- Refactor and clean up code
- Ensure all tests pass
4. After Completion
⚠️ Important: All checks must pass before each commit!
- Run
cargo fmt --all- Code formatting - Run
cargo clippy --workspace -- -D warnings- Static analysis, must have zero warnings - Run
cargo test --workspace- Unit tests, must all pass - Only create a git commit after all above checks pass
- Commit message format:
feat(phase-N): <description> - Example:
feat(phase-1): implement alias commands and core infrastructure
- Commit message format:
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.
- yesterday First seen · 399 lines · 2,685 tokens per session scan A 6f3d9d384467
cli AGENTS.md is an instructions file published in the GitHub repository rustfs/cli (133 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,685 tokens to every session, about $0.0134 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
console AGENTS.md
Instructions for rustfs/console, covering repository guidelines, project structure & module organization, build, test, and development commands, quality gates — must pass before every commit and engineering principles.
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.