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/thisisgm/omarchy-pods/agents-mdgit clone --depth 1 https://github.com/thisisgm/omarchy-podsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/thisisgm/omarchy-pods/agents-md)<a href="https://agentmods.dev/instructions/thisisgm/omarchy-pods/agents-md"><img src="https://agentmods.dev/badge/instructions/thisisgm/omarchy-pods/agents-md.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00972 | $0.00972 |
| Opus 5 | $0.00486 | $0.00486 |
| Sonnet 5 | $0.00194 | $0.00194 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
omarchy-pods 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 4d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Read CONTRIBUTING.md first. It is the contract for everybody, and nothing here replaces it. This file adds the handful of things coding agents get wrong in this repo specifically.
Agent-authored PRs are welcome and several are already merged. They are held to the same bar as any other, which in practice means the review will ask for evidence rather than for confidence.
The build, once
cd daemon
cmake -B build -G Ninja
cmake --build build
ctest --test-dir build
Two traps that have cost real time here:
daemon/tests/CMakeLists.txtlinks onlyQt6::TestandQt6::Core, so a test that reaches BlueZ, PulseAudio orQt6::Widgetscannot exist. Do not "fix" that by widening the link line. Move the logic somewhere testable instead.- If you build on one machine and run on another, do not trust an incremental
build after copying sources with preserved timestamps.
rsync -acan leave a source older than the object built from it, and the compiler will skip it. This produces a green run of code you never compiled.
What gets a change sent back
- Unrequested generality. A parameter with one caller, a mode nothing runs, a guard for a state this platform cannot reach. Delete it and say what the platform actually does.
- Comment paragraphs. One line, stating the constraint. Two or three only for a real timing or race constraint.
- A green suite offered as proof. Run the failing case first and show it red. If you cannot drive the defect, say that instead of implying you did.
- Invented abbreviations and em dashes. Both are in CONTRIBUTING.md and both are checked.
- AI attribution. No
Co-Authored-Byfor a tool, no "Generated with" line, anywhere: commits, PR bodies, comments.
The output codec is not negotiable
The daemon selects the highest-bitrate playback profile the card offers, SBC-XQ at 453 kbps ahead of SBC at 328 and AAC at 256, and re-applies it on every activation because PipeWire's priority order puts AAC first. A change that lowers the selected bitrate is a defect here even when it reads as a simplification, and a guard that quietly skips the selection is the same defect in a different costume. One of those has already shipped and been reverted.
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.
- 4d ago First seen · 84 lines · 972 tokens per session scan A 89929b59e835
omarchy-pods AGENTS.md is an instructions file published in the GitHub repository thisisgm/omarchy-pods (176 stars, last pushed 9d ago), licensed MIT. It adds 972 tokens to every session, about $0.0049 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
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).
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.
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.