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/ahmetb/iris/agents-mdgit clone --depth 1 https://github.com/ahmetb/IrisWhat 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 | $0.01281 | $0.01281 |
| Opus 5 | $0.00641 | $0.00641 |
| Sonnet 5 | $0.00256 | $0.00256 |
| Haiku 4.5 | $0.00128 | $0.00128 |
Grade A, and why
Iris 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Development Principles for Iris.app
Project Overview
Iris is a macOS application that displays a webcam feed in a circular, always-on-top window. This is an LLM-agent-coded project where the human developer provides feedback but does not write code directly.
Core Development Principles
1. No Xcode IDE Required
- All development must be possible via command-line tools
- Provide
build.shandrun.shscripts for easy compilation and launch - Use
xcodebuildfor building, not Xcode IDE - Developer should only need: macOS, Command Line Tools, and a terminal
2. Design-First Approach
- Every feature has a corresponding
design/*.mdfile - Read the design doc before implementing a feature
- Design docs specify:
- High-level architecture
- Key classes and their responsibilities
- Edge cases and gotchas
- Testing considerations
3. Code Quality Standards
Simplicity Over Cleverness
- Write straightforward, readable code
- Avoid premature optimization
- No unnecessary abstractions
- Clear naming over comments
Native macOS Patterns
- Use AppKit (not SwiftUI) for precise window control
- Follow Apple's Human Interface Guidelines
- Leverage native APIs (AVFoundation, NSStatusBar, etc.)
- Handle macOS-specific behaviors properly
Error Handling
- Gracefully handle camera permissions denial
- Handle no camera available scenario
- Handle window positioning on disconnected displays
- Log errors clearly for debugging
4. Incremental Development
- Build features one at a time
- Each feature should be testable independently
- Commit working code frequently
- Don't break existing functionality
5. Performance Considerations
- Video rendering should be smooth (60fps target)
- Minimize CPU usage when idle
- Efficient memory usage for video buffers
- Window resizing should be responsive
6. User Experience
- No crashes or unexpected behavior
- Smooth animations and transitions
- Clear error messages
- Sensible defaults
- Remember user preferences
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 · 165 lines · 1,281 tokens per session scan A 84df09b5e6d0
Iris AGENTS.md is an instructions file published in the GitHub repository ahmetb/Iris (59 stars, last pushed 23d ago), licensed MIT. It adds 1,281 tokens to every session, about $0.0064 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
FluidAudio copilot-instructions.md
Instructions for FluidInference/FluidAudio, covering fluidaudio - agent development guide, build & test commands, architecture, critical rules and code style (swift-format config).
speech-swift AGENTS.md
Instructions for soniqo/speech-swift, covering agent instructions, communication style, workflow, running tests and benchmarks — sequential and memory-aware and git conventions.
codex-provider-sync AGENTS.md
Instructions for Dailin521/codex-provider-sync, covering ai / agent operator guide, vnext architecture baseline, goal, choose the interface and safe operating flow.
liney AGENTS.md
Instructions for everettjf/liney, covering liney repository collaboration guide, 交流语言 / communication language, project overview, repository layout and build and test.
Starcat AGENTS.md
Instructions for starcat-app/Starcat, covering agents.md, 🚨 硬性铁律(每次写代码前必读,违反即返工), 🌿 git 分支与 worktree(强制), 🧭 主进度索引(每次开工前必读) and 状态符号(与功能实现总览.md 同步).
skills-manager CLAUDE.md
Instructions for yibie/skills-manager, covering skills manager - development guide, tui engine: blessed, 核心原则, 参考文档 and 正确的 list 用法.