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/AGENTS.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/agents-md)<a href="https://agentmods.dev/instructions/aby-agency/aby-claude-watcher/agents-md"><img src="https://agentmods.dev/badge/instructions/aby-agency/aby-claude-watcher/agents-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/agents-md"><img src="https://agentmods.dev/badge/instructions/aby-agency/aby-claude-watcher/agents-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 | $0.00625 | $0.00625 |
| Opus 5.5 | $0.00250 | $0.00250 |
| Sonnet 5.5 | $0.00125 | $0.00125 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
aby-claude-watcher AGENTS.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 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.
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 — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - aby-claude-watcher
Ce dépôt n'a qu'une constitution : CLAUDE.md, à la racine. Elle vaut pour tout agent de code, quel que soit l'outil qui lit ce fichier (Codex, Claude Code, autre). Lis-la en entier avant d'écrire une ligne.
Les règles qui se vérifient par une commande :
- Un worktree par ticket, créé depuis
origin/maindans~/Aby/.worktrees/aby-claude-watcher/<ticket>, jamais ailleurs. Vérifier :git worktree list. - Rien ne reste non commité en fin de session. Vérifier :
git status --shortvide. - Historique linéaire : rebase sur
origin/main, jamais de merge demaindans une branche. Vérifier :git rev-list --merges origin/main..HEADvide. - « Terminé » se prouve : on donne les codes de sortie et les compteurs des vérifications locales, pas « testé en local ».
- Un ticket, une issue, des commits à son numéro (
feat(#N): ...), une PR qui porteCloses #N. - Une demande d'Etienne s'écrit dans l'issue avant d'être codée, citée mot pour mot et datée ; rien ne se « rétablit » sans vérifier d'où ça vient (
gh search issues,registres/journal.md).
Ce que Codex fait à la main
Les hooks de .claude/settings.json ne tournent que dans Claude Code. Sous Codex, les mêmes gardes se tiennent à la main :
- Démarrage :
node scripts/registres.mjs check; s'il dit « consolidation due »,node scripts/registres.mjs rotatepuis commitdocs: rotation des registres. Lire le sommaire d'ADR, le sommaire de LRN et l'ouvert de TASKS. - Interdits (deny list de Claude) : suppression récursive forcée,
git push --force/-f,git reset --hard, écrire dans un.env(sauf.env.example), écrire dans.git/. Action destructive, envoi externe ou écriture en prod : validation d'Etienne d'abord. - Avant de pousser : les vérifications locales du projet passent (codes de sortie lus), une poussée par lot, pas de tag sans raison (minutes d'intégration continue comptées).
- Fin de session : rien de non commité dans
registres/; décidé (ADR), appris (LRN), coincé (TASKS), une entrée de journal.
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.
- 12d ago First seen · 24 lines · 625 tokens per session scan A 6a543a79e4fc
aby-claude-watcher AGENTS.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 625 tokens to every session, about $0.0025 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 2026-10-16.
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).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.