Borrowing it
Nothing to install: this file belongs to aby-agency/aby-claude-watcher. 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/aby-agency/aby-claude-watcher/main/CLAUDE.mdgit clone --depth 1 https://github.com/aby-agency/aby-claude-watcherWrote 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/aby-agency/aby-claude-watcher/claude-md)<a href="https://agentmods.dev/instructions/aby-agency/aby-claude-watcher/claude-md"><img src="https://agentmods.dev/badge/instructions/aby-agency/aby-claude-watcher/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/aby-agency/aby-claude-watcher/claude-md"><img src="https://agentmods.dev/badge/instructions/aby-agency/aby-claude-watcher/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 | $0.14350 | $0.14350 |
| Opus 5 | $0.07175 | $0.07175 |
| Sonnet 5 | $0.02870 | $0.02870 |
| Haiku 4.5 | $0.01435 | $0.01435 |
Grade B, and why
aby-claude-watcher 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 2d 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.
- **Détection « en attente » = hook GLOBAL (v2.4.0), signal `PermissionRequest` (v2.12.0).** Le pending (permission prompt) n'est visible que via un hook Claude Code qui ping le socket. **Le hook installé est `Permission How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aby Claude Watcher
Electron desktop app monitoring Claude Code sessions in real-time.
Dev
npm install
npm start # production
npm run dev # with devtools
npm run build # DMG — REQUIERT Node ≥ 20.19 (cf. .nvmrc: 22)
Node ≥ 20.19 obligatoire pour
npm install/npm run build. Depuis Electron 41.8+, son downloader@electron/getest passé en ESM pur : le postinstallrequire()casse (ERR_REQUIRE_ESM) sur Node < 20.19.nvm uselit le.nvmrc(Node 22). Le champenginesdu package.json documente la contrainte.
PIÈGE
build.files(liste blanche electron-builder). Tout nouveau module racine chargé parrequire('./x')DOIT être ajouté àbuild.filesdans package.json, sinonnpm run devmarche mais l'app installée plante au démarrage (« Cannot find module './x' », visible seulement dans main.log — DMG 2.13.0 cassé avant release, presence.js / bg-task.js oubliés).test/build-files.test.jsvérifie la fermeture transitive depuis main.js.
Architecture
main.js— Electron main process, window, IPC, traywatcher.js— Session discovery (~/.claude/sessions/), JSONL parsing, state machinesocket.js— Unix socket IPC forcc/cwawrappersfocus.js— Terminal focus (AppleScript iTerm2/Terminal/Warp), resume, launchconfig.js— Persistence (debounced writes, saveSync on shutdown)preload.js— Context bridge (contextIsolation: true)island.js+island-model.js— Dynamic island ancrée à l'encoche (fenêtre transparente + logique pure testée)ui/— Renderer (vanilla HTML/CSS/JS, no framework)
States
| State | Color | Trigger |
|---|---|---|
| thinking | purple #a78bfa |
Last event = user text (Claude processing) |
| running | blue #3b82f6 |
Last event = assistant with stop_reason: "tool_use" |
| waiting | green #22c55e |
status: idle/shell de session.json (CLI ≥ 2.1.260) ; sinon end_turn + 2s no activity. Si des tâches de fond sont encore ouvertes (status: shell ou JSONL) : chip cyan « N bg process » + notifs mutées, l'état reste waiting |
| delegating (« Délégation ») | cyan #06b6d4 |
waiting alors que des sous-agents / un workflow / une tâche Bash de fond reconnue (pas un serveur) travaillent encore, ou que le CLI se dit busy — état de PRÉSENTATION calculé par main.js, ne notifie pas |
| pending | amber #f59e0b |
status: waiting (sauf waitingFor: dialog open) ; hook PermissionRequest pour l'instantanéité |
| error | red #ef4444 |
isApiErrorMessage event OR silent crash after explicit resume |
| completed | (purged) | Session file gone + PID dead → removed from UI |
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.
- 2d ago Changed · +8 lines · +2,767 tokens per session 53ee97d8e13e
- 6d ago Changed · +809 tokens per session 50efb92c7bdc
- 10d ago First seen · 86 lines · 10,774 tokens per session scan B 806a6c0a2fde
aby-claude-watcher CLAUDE.md is an instructions file published in the GitHub repository aby-agency/aby-claude-watcher (2 stars, last pushed 2d ago), licensed MIT. It adds 14,350 tokens to every session, about $0.0717 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
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.
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).
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.
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).
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.