Borrowing it
Nothing to install: this file belongs to iaglourenco/needle. 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/iaglourenco/needle/main/CLAUDE.mdgit clone --depth 1 https://github.com/iaglourenco/needleWrote 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/iaglourenco/needle/claude-md)<a href="https://agentmods.dev/instructions/iaglourenco/needle/claude-md"><img src="https://agentmods.dev/badge/instructions/iaglourenco/needle/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 | $0.01601 | $0.01601 |
| Opus 5 | $0.00800 | $0.00800 |
| Sonnet 5 | $0.00320 | $0.00320 |
| Haiku 4.5 | $0.00160 | $0.00160 |
Grade B, and why
needle CLAUDE.md scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- `needle.exe remove-hooks` → strips Needle's entries from `~/.claude/settings.json` (called by the NSIS uninstaller pre-uninstall hook). How it starts
The opening of the file, as written. The whole thing — 54 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.
What this is
Needle: Windows tray app (Tauri 2 + Vue 3 frontend, Rust backend) that monitors Claude Code sessions. Claude Code fires hooks on session events; Needle's own executable (needle.exe hook) receives them, forwards to the running app over local HTTP, and the app tracks per-session state in SQLite, updating the tray icon/panel live.
Commands
npm install
npm run tauri dev # dev mode (Vite + Tauri, hot reload)
npm run build # vue-tsc --noEmit && vite build (frontend only)
npm run tauri build # release build, NSIS installer at src-tauri/target/release/bundle/nsis
cd src-tauri
cargo test # all Rust unit tests
cargo test <name> # single test by substring, e.g. cargo test transition
CI (.github/workflows/release.yml) on tag push v*: vue-tsc --noEmit + cargo test, then builds/publishes via tauri-apps/tauri-action.
Prerequisites: Rust (MSVC toolchain), Visual Studio Build Tools (C++ workload), Node.js 20+.
Architecture
Dual entry point of the same binary
src-tauri/src/main.rs branches on argv[1] before any Tauri init:
needle.exe hook→hookmode::run(): reads a hook JSON payload from stdin, POSTs it to the running app's local HTTP server, exits. No GUI, no Tauri — this is what Claude Code actually invokes on every hook event, so it must stay fast and fail silently (a dead/unreachable app must never block a Claude Code session).needle.exe remove-hooks→ strips Needle's entries from~/.claude/settings.json(called by the NSIS uninstaller pre-uninstall hook).- no args → normal Tauri app: opens the local HTTP server, tray icon, webview window, background cleanup job.
Event flow
hookmode → local HTTP (server.rs, axum, POST /event) → state::transition(current, event) (pure state machine, see state.rs) → db::upsert_session (SQLite, db.rs) → tray::on_session_changed (tray.rs): re-reads the session's Claude Code transcript for cost/model, updates tray tooltip, emits session-updated to the webview, and alerts (tray::alert_if_needed) if the new state warrants it — an OS notification when Settings.notifications_enabled is on, otherwise an in-app toast (toast.rs's toast::show, emits toast-show to the dedicated toast window, which navigates to the main panel via the open_panel_from_toast command when clicked). session-removed is emitted only from main.rs — on the 24h stale-purge in spawn_cleanup_job and on manual deletion via the delete_session command — never from tray.rs.
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 · 54 lines · 1,601 tokens per session scan B 307d7e83fc29
needle CLAUDE.md is an instructions file published in the GitHub repository iaglourenco/needle (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,601 tokens to every session, about $0.0080 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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.
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.
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).
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.