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/walshydev/orb/agents-mdgit clone --depth 1 https://github.com/WalshyDev/orbWhat 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 | $0.01810 | $0.01810 |
| Opus 5 | $0.00905 | $0.00905 |
| Sonnet 5 | $0.00362 | $0.00362 |
| Haiku 4.5 | $0.00181 | $0.00181 |
Grade A, and why
orb 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guide for Orb
This file provides guidance specifically for AI agents (and humans) working on this codebase. Read AGENTS.md first for full architecture, project structure, and design principles. This file supplements it with practical details, gotchas, and quick references.
Quick Start
make build # Debug build (fast, use for iterating)
make test # Run all tests
make lint # Check formatting + clippy (CI runs this)
make fix # Auto-fix formatting + clippy issues
Always run make lint before submitting changes. CI will reject PRs that fail lint.
Rust Edition & Toolchain
- Edition: Rust 2024 (
edition = "2024"in all Cargo.toml files) - MSRV: 1.91 (set in all three package Cargo.toml files)
- No rust-toolchain.toml - uses whatever stable/beta toolchain the developer has installed
- Note:
CONTRIBUTING.mdsays "Rust 1.90 (nightly)" — this is outdated. The actual MSRV is 1.91 from Cargo.toml.
Workspace Structure
Cargo.toml # Workspace root (resolver = "2")
packages/
orb-cli/ # Binary: `orb` (publish = false)
orb-client/ # Library (publish = false, designed as standalone)
orb-mockhttp/ # Mock server library (publish = true)
Critical Rules
1. Client/CLI Separation
orb-client must NEVER import from or depend on orb-cli. This is the most important architectural constraint.
- Adding verbose output? Add a new
ClientEventvariant inpackages/orb-client/src/events.rs, then handle it inpackages/orb-cli/src/verbose_events.rs. - Adding error handling? Use
OrbErrorvariants inorb-client, map to user-friendly messages viafatal!inorb-cli. - Never use
fatal!inorb-client— it's a CLI macro. UseOrbErrorand propagate with?.
2. Crypto Provider
Both orb-client and orb-mockhttp use aws-lc-rs as the TLS crypto provider:
let _ = rustls::crypto::aws_lc_rs::default_provider().install_default();
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 · 171 lines · 1,810 tokens per session scan A cc91f3ae5346
orb AGENTS.md is an instructions file published in the GitHub repository WalshyDev/orb (11 stars, last pushed 5mo ago), licensed MIT. It adds 1,810 tokens to every session, about $0.0090 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
igniter-js GEMINI.md
Gemini CLI instructions for felipebarcelospro/igniter-js, covering 1. identity and profile, 2. about the igniter.js monorepo, 3. personality and communication, 4. lia's core responsibilities (the 4 pillars) and 5. technical guidelines and methodology.
igniter-js AGENTS.md
AGENTS.md instructions for felipebarcelospro/igniter-js, covering lia - ai agent for igniter.js, 1. identity & mission, core mission, key responsibilities and 2. project overview.
igniter-js writing-style.instructions.md
Instructions for felipebarcelospro/igniter-js, covering ✍️ unified documentation style guide (for llms & authors), 🎯 core style principles (applies to all documentation), 📘 documentation (docs): writing style, installation and quick start.
moclojer AGENTS.md
Instructions for moclojer/moclojer, covering agents.md, project overview, development commands, run the server and run all tests.
igniter-js writing-guidelines.instructions.md
Instructions for felipebarcelospro/igniter-js, covering writing guidelines for humans and llms, core style principles, fumadocs-specific guidelines, available mdx components and component usage examples.
moclojer copilot-instructions.md
Instructions for moclojer/moclojer, a project described as: Simple and efficient HTTP and Webscoket mock server with specification in yaml, edn or OpenAPI.