Borrowing it
Nothing to install: this file belongs to abhiunix/AgentHarbor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/abhiunix/AgentHarbor/main/CLAUDE.mdgit clone --depth 1 https://github.com/abhiunix/AgentHarborWrote 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/abhiunix/agentharbor/claude-md)<a href="https://agentmods.dev/instructions/abhiunix/agentharbor/claude-md"><img src="https://agentmods.dev/badge/instructions/abhiunix/agentharbor/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/abhiunix/agentharbor/claude-md"><img src="https://agentmods.dev/badge/instructions/abhiunix/agentharbor/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02538 | $0.02538 |
| Opus 5.5 | $0.01015 | $0.01015 |
| Sonnet 5.5 | $0.00508 | $0.00508 |
| Haiku 4.5 | $0.00254 | $0.00254 |
Grade A, and why
AgentHarbor 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 1mo 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
npm install # install JS deps
npm run tauri dev # full dev: Vite on :1420 + Tauri window, Rust hot-restart
npm run build # tsc && vite build (frontend only)
npm run test:regression # npm run build + cd src-tauri && cargo test (the CI gate)
Targeted checks:
npx tsc --noEmit # frontend type check (CI uses this)
cd src-tauri && cargo test <name> # single Rust test
cd src-tauri && cargo clippy --all-targets -- -D warnings # lint Rust (CI runs this, continue-on-error)
cd src-tauri && SKIP_VERSION_BUMP=1 cargo build # build check without bumping the patch version
Version-bump side effect. npm run build runs scripts/bump-build.cjs as a prebuild step and increments the patch in package.json, src-tauri/tauri.conf.json, and src-tauri/Cargo.toml in lockstep. Set SKIP_VERSION_BUMP=1 whenever you don't want that (CI sets it on plain build checks; the signed-release flow also sets it — see docs/build-and-release.md).
Signed/notarized builds, release tagging, and the latest.json updater feed are documented in docs/build-and-release.md; do not run them speculatively.
Architecture
Tauri 2 desktop app. React 19 + TypeScript + Vite + Zustand (src/) talks over Tauri IPC to a Rust backend (src-tauri/src/). Bundle target is macOS aarch64 + Windows x64; no Linux packaging.
Two Tauri windows
src/App.tsx branches on getCurrentWindow().label:
main— the full app (sidebar + routes underBrowserRouter).tray-popover— a separate Tauri window owned bysrc-tauri/src/tray.rs, renders<TrayPopover />only. It emitsnavigate-toevents that the main window picks up viaNavigateListener(also shows/focuses the main window).
Adapter trait — the core abstraction
src-tauri/src/adapters/traits.rs defines AgentAdapter (id, name, capabilities, detect, read_config, diff, deploy, remove, managed_paths). One implementation per provider (claude_code, cursor, windsurf, gemini, copilot, antigravity, vscode, codex) lives next to it. AdapterRegistry::new() in adapters/mod.rs instantiates the full list — adding a provider means adding it there.
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.
- 1mo ago First seen · 132 lines · 2,538 tokens per session scan A 0813df243f93
AgentHarbor CLAUDE.md is an instructions file published in the GitHub repository abhiunix/AgentHarbor (14 stars, last pushed today), licensed MIT. It adds 2,538 tokens to every session, about $0.0102 per session on Opus 5.5. 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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.