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/bitwize-ai/logue/claude-mdgit clone --depth 1 https://github.com/bitwize-ai/LogueWrote 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/bitwize-ai/logue/claude-md)<a href="https://agentmods.dev/instructions/bitwize-ai/logue/claude-md"><img src="https://agentmods.dev/badge/instructions/bitwize-ai/logue/claude-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 5.1 | $0.07535 | $0.07535 |
| Opus 5 | $0.03768 | $0.03768 |
| Sonnet 5 | $0.01507 | $0.01507 |
| Haiku 4.5 | $0.00754 | $0.00754 |
Grade A, and why
Logue CLAUDE.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 6d 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 — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Logue — Development Guidelines
Project Overview
macOS app (macOS 26+ / Tahoe): AI-powered meeting notes + document editing. Privacy-first — all AI inference, transcription, and data processing runs locally on-device via MLX. By default nothing leaves the laptop; the only network calls are on-device model downloads, Sparkle update checks, and opt-in features the user explicitly enables (web search, external AI providers).
- Bundle ID:
com.bitwize.logue - Source:
Logue/, Tests:LogueTests/ - Swift 5.9 + SwiftUI + AppKit
- Build system: XcodeGen — run
xcodegen generateafter adding new.swiftfiles or changingproject.yml - Build (runnable):
xcodebuild build -project Logue.xcodeproj -scheme Logue -destination 'platform=macOS' DEVELOPMENT_TEAM=HC5R66SXM5 CODE_SIGN_STYLE=Automatic - Build / test (compile-check only): append
CODE_SIGNING_ALLOWED=NO CODE_SIGNING_REQUIRED=NO CODE_SIGN_IDENTITY="" - MLX prerequisite:
xcodebuild -downloadComponent MetalToolchain - Test (LLM integration):
xcodebuild test -project Logue.xcodeproj -scheme Logue -destination 'platform=macOS' -only-testing:LogueTests/<SuiteName>
xcodebuildwith no signing arguments fails, and the error —"Logue" has entitlements that require signing with a development certificate— reads like a code error rather than a missing flag.project.ymlshipsDEVELOPMENT_TEAM: ""deliberately, so the team is passed on the command line and never committed.
Running the build you just made
Three separate things will each hand you a different build than the one you compiled, and all three fail silently — the app launches, looks right, and simply does not contain your change. Every "my edit isn't showing up" report so far has been one of these, not a bug in the code.
- Never pick the app by timestamp. More than one DerivedData root exists for this project (the command line's and Xcode's). Ask the build system where it writes, rather than guessing:
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.
- 6d ago First seen · 378 lines · 7,535 tokens per session scan A 9b8e2e8f7573
Logue CLAUDE.md is an instructions file published in the GitHub repository bitwize-ai/Logue (167 stars, last pushed yesterday), licensed MIT. It adds 7,535 tokens to every session, about $0.0377 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
apfel CLAUDE.md
Instructions for Arthur-Ficial/apfel, covering apfel - project instructions, the golden goal, core product (this is what apfel is), byproducts (useful, but not the pitch) and readme.md structure rule.
speech-swift AGENTS.md
AGENTS.md instructions for soniqo/speech-swift, covering agent instructions, communication style, workflow, running tests and benchmarks — sequential and memory-aware and git conventions.
Vocello AGENTS.md
AGENTS.md instructions for PowerBeef/Vocello, covering agents.md — vocello (qwenvoice), product and authority, start and resume work, release-first execution and hard invariants.
localvoxtral AGENTS.md
AGENTS.md instructions for T0mSIlver/localvoxtral, covering localvoxtral — agent guide, build & test — read this first on a non-mac dev box, proof culture — non-negotiable, test tiers — the short version and ci / shipping.
OpenSuperMLX AGENTS.md
AGENTS.md instructions for axot/OpenSuperMLX, covering agents.md — opensupermlx, agent behavioral guidelines, 1. think before coding, 2. simplicity first and 3. surgical changes.
Rapid-MLX AGENTS.md
AGENTS.md instructions for raullenchai/Rapid-MLX, covering rapid-mlx engineering team, team, working model, required task lifecycle and durable knowledge.