agentmods.dev

openquack AGENTS.md

openquack AGENTS.md is an instructions file for Codex, OpenCode from larryxiao/openquack. It costs 1,328 tokens per session, scanned A, original, MIT.

A set of contribution rules for the OpenQuack project, covering specifications, pull requests, tests, and source checking.

In plain words
What is it for?
Use it when writing specs, splitting work into focused pull requests, adding tests, documenting benchmark results, or checking technical details against primary sources.
Why use it?
It gives contributors a shared way to define work and prove that changes meet their goals. A pull request is a proposed code change for review.

Instructions file for CodexOpenCode

not rated 52 3d ago A scan 1,328 tokens original MIT
View the source file larryxiao/openquack
Install

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.

agentmods
npx agentmods add instructions/larryxiao/openquack/agents-md
Clone the repo
git clone --depth 1 https://github.com/larryxiao/openquack

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for openquack AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/larryxiao/openquack/agents-md.svg)](https://agentmods.dev/instructions/larryxiao/openquack/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/larryxiao/openquack/agents-md"><img src="https://agentmods.dev/badge/instructions/larryxiao/openquack/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,328 This file is loaded in full into every session.
When invoked 1,328 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01328 $0.01328
Opus 5 $0.00664 $0.00664
Sonnet 5 $0.00266 $0.00266
Haiku 4.5 $0.00133 $0.00133

Measured 4d ago against content hash 79af0c8e0135, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

openquack 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.

AGENTS.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

How AI agents (and humans) should contribute to OpenQuack. Most rules apply equally to both — humans can ignore the bits about advisor calls.

Posture

  • Specs are the contract. Every PR cites a SPEC-XXX. If no spec covers your change, write the spec first (one PR adds the spec; a follow-up PR implements).
  • Specs must include clear goals and how to validate them. Every spec's ## Acceptance criteria section states what the feature is trying to achieve and exactly how to confirm it — a user-visible behaviour ("pastes within 200 ms of hotkey release"), a measurable metric ("WER ≤ 6.5 % on the noisy corpus"), or explicit manual steps a reviewer can follow. A spec without this is still a proposal; don't start implementation until the goal and its validation method are written down.
  • Atomic PRs. One spec, one milestone task. If your work touches multiple concerns, split it.
  • Tests are non-optional. Touch a metric → bench delta documented in the PR. Touch logic → unit test added. Touch UX → the PR describes how to repro manually.
  • Cite primary sources, not memory. When you need WhisperKit specifics, read .build/checkouts/argmax-oss-swift/Sources/WhisperKit/Core/.... When you need bench math, read Sources/OpenQuackKit/Metrics/.
  • Do the work, don't narrate it. PR descriptions describe the change and why, not what you tried.

Before you start

  1. Read docs/VISION.md, docs/ROADMAP.md, this file. Skim docs/BENCHMARKS.md.
  2. Pick a 🔵 task in ROADMAP.md.
  3. Read the cited SPEC under docs/SPECS/.

Workflow

  1. Open a draft PR early — even with just a one-line description and a stub change. Push small, test often.
  2. Run before pushing (use Xcode's toolchain; the system swift 6.1.x lacks the PreviewsMacros plugin that KeyboardShortcuts depends on, so a bare swift build fails on a clean checkout): 
    DEVELOPER_DIR=/Applications/Xcode.app/Contents/Developer swift build
DEVELOPER_DIR=/Applications/Xcode.app/Contents/Developer swift test
    CI uses the same toolchain, so the override matches reality.
  3. If your change might affect transcription quality or latency, also: 
    DEVELOPER_DIR=/Applications/Xcode.app/Contents/Developer swift run openquack-bench --models tiny --corpus bench/corpus/short
    and report the delta in the PR.
  4. Mark the PR ready for review when CI is green and your tests cover the change.

Read the full file on GitHub · 101 lines

Changes

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.

  1. 4d ago First seen · 101 lines · 1,328 tokens per session scan A 79af0c8e0135

Subscribe to this mod's changes

openquack AGENTS.md is an instructions file published in the GitHub repository larryxiao/openquack (52 stars, last pushed 3d ago), licensed MIT. It adds 1,328 tokens to every session, about $0.0066 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.

Apple SiliconProductivitydictationlocal-firstmacosmenu-barprivacy
Related

Other instructions, from other repositories

macparakeet AGENTS.md

AGENTS.md instructions for moona3k/macparakeet, covering agents.md -- macparakeet, project shape, commands, worktrees and code boundaries.

moona3k/macparakeet · 2,107 tokens

macparakeet CLAUDE.md

Claude Code instructions for moona3k/macparakeet, covering claude.md, claude-specific rules, local-state cautions and references.

moona3k/macparakeet · 448 tokens

humla CLAUDE.md

Claude Code instructions for michaelwilhelmsen/humla, covering humla — project notes, what this app is, core capabilities, architecture overview and data flow during a recording.

michaelwilhelmsen/humla · 19,981 tokens

os-clovy AGENTS.md

AGENTS.md instructions for open-software-network/os-clovy, covering clovy — agent instructions, project, os platform (shared brain), structure and domain & decisions — read before writing code.

open-software-network/os-clovy · 4,092 tokens

humla AGENTS.md

AGENTS.md instructions for michaelwilhelmsen/humla, covering humla — project notes, what this app is, core capabilities, architecture overview and data flow during a recording.

michaelwilhelmsen/humla · 6,738 tokens

cai CLAUDE.md

Instructions for cai-layer/cai, covering claude.md, what is cai?, design system, build & run and dev.

cai-layer/cai · 3,988 tokens