agentmods.dev

aby-claude-watcher: Instructions file for Claude Code

CLAUDE.md

aby-claude-watcher CLAUDE.md is an instructions file for Claude Code from aby-agency/aby-claude-watcher. It costs 17,953 tokens per session, scanned D, original, MIT.

Development instructions for an Electron desktop app that watches Claude Code sessions in real time. They describe its architecture, session states, development commands, and key design decisions.

In plain words
What is it for?
Maintaining the watcher, working on session discovery and state handling, changing the macOS interface, and building or testing the app.
Why use it?
They give a coding agent the project context needed to change the app safely, including its Node.js requirement and how its processes communicate.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

This is aby-agency/aby-claude-watcher's own configuration. It tells Claude Code how to work on aby-claude-watcher itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything aby-claude-watcher configures →

not rated 2repo changed 12d ago D scan 17,953 tokens original MIT
View source ↗ aby-agency/aby-claude-watcher
Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/aby-agency/aby-claude-watcher/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/aby-agency/aby-claude-watcher

Made for: Claude Code.

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 aby-claude-watcher CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/aby-agency/aby-claude-watcher/claude-md/github.svg)](https://agentmods.dev/instructions/aby-agency/aby-claude-watcher/claude-md)
Your own site
<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.

agentmods 80×15 button for aby-claude-watcher CLAUDE.md

Your own site · 80×15
<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>
Per session 17,953 This file is loaded in full into every session.
When invoked 17,953 The same file — it is already loaded in full.
Security scan D 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.17953 $0.17953
Opus 5.5 $0.07181 $0.07181
Sonnet 5.5 $0.03591 $0.03591
Haiku 4.5 $0.01795 $0.01795

Measured 12d ago against content hash 2d81cdba72da, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

aby-claude-watcher CLAUDE.md scanned grade D with 2 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 12d 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

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **« Action requise » dit CE QU'ELLE DEMANDE (v2.16.0).** Le badge ambre annonçait qu'il fallait répondre, jamais à quoi : il fallait ouvrir la session pour l'apprendre — or l'information arrivait déjà. Le payload `Perm
CLAUDE.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 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/get est passé en ESM pur : le postinstall require() casse (ERR_REQUIRE_ESM) sur Node < 20.19. nvm use lit le .nvmrc (Node 22). Le champ engines du package.json documente la contrainte.

PIÈGE build.files (liste blanche electron-builder). Tout nouveau module racine chargé par require('./x') DOIT être ajouté à build.files dans package.json, sinon npm run dev marche 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.js vérifie la fermeture transitive depuis main.js.

Tickets et worktrees

  • Tickets : issues GitHub du dépôt (gabarit .github/ISSUE_TEMPLATE/ticket.md, labels fermés epic:…, taille:XS|S|M|L|XL, bloqué, backlog). Une session = une issue, prise par assignation (gh issue edit N --add-assignee @me), branche ticket/N-slug, commits feat(#N): … / fix(#N): …, PR dont la description porte Closes #N, fusion quand les critères sont cochés. Lecture par gh filtré (--label, --state, --limit, --json), jamais sans filtre, jamais le serveur MCP GitHub.
  • Commits en français ; dates YYYY-MM-DD.
  • Worktrees : un par ticket, ~/Aby/.worktrees/aby-claude-watcher/<ticket> depuis origin/main, jamais à côté du dépôt ; retiré dès que la PR est fusionnée ou fermée ; six vivants au plus.

Règles non-négociables

  • Aucune signature Claude/AI dans le code, les commits, les PR (constitution Aby § 2).
  • Ne jamais renommer ou supprimer le cwd de la session Claude en cours (constitution § 2).
  • Pas de fallback silencieux : si une étape échoue, escalader (constitution § 2).
  • main doit toujours builder.
  • Critères de succès des tickets : binaires + mesurables + conditions d'arrêt. On coche, on ne « sent » pas.
  • Une demande d'Etienne donnée en conversation s'écrit dans l'issue, citée et datée, avant d'être codée ; on ne « rétablit » jamais un état disparu sans avoir vérifié qu'il ne vient pas d'une de ses demandes (issues, journal).
  • Les minutes d'intégration continue sont comptées (3 000 par mois pour tous les dépôts d'Aby Agency) : vérifications locales AVANT toute poussée, une poussée par lot cohérent, aucun rejeu réflexe d'un run rouge, et un commit qui ne touche que docs/ ou registres/ ne déclenche aucune chaîne (message terminé par [skip ci]).

Read the full file on GitHub · 129 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. 12d ago Changed · +31 lines · +903 tokens per session 2d81cdba72da
  2. 1mo ago Changed · +3 lines · +1,715 tokens per session scan B → D ae62c5ba483b
  3. 1mo ago Changed · +1 lines · +985 tokens per session 330ec4e48523
  4. 1mo ago Changed · +8 lines · +2,767 tokens per session 53ee97d8e13e
  5. 1mo ago Changed · +809 tokens per session 50efb92c7bdc
  6. 1mo ago First seen · 86 lines · 10,774 tokens per session scan B 806a6c0a2fde

Subscribe to this mod's changes

aby-claude-watcher CLAUDE.md is an instructions file published in the GitHub repository aby-agency/aby-claude-watcher (2 stars, last pushed 4d ago), licensed MIT. It adds 17,953 tokens to every session, about $0.0718 per session on Opus 5.5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,461 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,731 tokens

vscode model-prompts.instructions.md

Model-specific prompt authoring and registry guidelines.

microsoft/vscode · 2,022 tokens