Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/pyroalpha/agent-center/claude-mdgit clone --depth 1 https://github.com/pyroalpha/agent-centerWhat 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 | $0.01740 | $0.01740 |
| Opus 5 | $0.00870 | $0.00870 |
| Sonnet 5 | $0.00348 | $0.00348 |
| Haiku 4.5 | $0.00174 | $0.00174 |
Grade A, and why
agent-center 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 3d 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 — 253 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.
Project Overview
AgentCenter is a task orchestration platform for Claude Code CLI that provides:
- Task state visualization and dependency orchestration
- Execution isolation via git worktree
- Real-time logging via WebSocket
Tech Stack:
- Backend: FastAPI (Python 3.13+) with SQLite (WAL mode)
- Frontend: Next.js 14, React 18, TypeScript, TailwindCSS
- Agent: Claude Code CLI (@anthropic-ai/claude-code)
Quick Commands
Backend
cd backend
# Development server
uvicorn app:app --host 0.0.0.0 --port 8010
# Or use the CLI entry point
uv sync
ac # Runs on default port 8010
# Run tests
pytest
# Lint and type check
ruff check .
mypy .
Frontend
cd frontend
# Development server
npm run dev # http://localhost:3010
# Production build
npm run build
npm run start
# Lint and type check
npm run lint
npm run type-check
Architecture
Backend Structure (backend/)
backend/
├── app.py # FastAPI entry point, WebSocket manager, lifespan
├── auth.py # Session-based authentication
├── config.py # Environment configuration
├── db.py # SQLite connection pool
├── middleware/
│ └── auth.py # Authentication middleware
├── routes/
│ ├── tasks.py # Task CRUD, execution, WebSocket logs
│ ├── plans.py # Plan approval workflow
│ ├── inbox.py # Idea inbox (暂存区)
│ ├── projects.py # Project management
│ ├── filesystem.py # File operations
│ ├── auth.py # Login/logout
│ └── status.py # System status
├── scheduler/
│ ├── loop.py # RalphLoop - main scheduler (polls every 5s)
│ └── worker.py # Worker pool management
├── services/
│ ├── task_service.py # Task business logic
│ ├── runner_service.py # Claude Code CLI runner (--fork-session, --resume)
│ ├── worktree_service.py # Git worktree create/merge/cleanup
│ ├── dependency_service.py # Task dependency resolution
│ └── plan_service.py # Plan mode handling
└── utils/
└── signals.py # Signal handling for graceful shutdown
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.
- 3d ago First seen · 253 lines · 1,740 tokens per session scan A bcde8d8cdf3a
agent-center CLAUDE.md is an instructions file published in the GitHub repository pyroalpha/agent-center (11 stars, last pushed 5mo ago), licensed MIT. It adds 1,740 tokens to every session, about $0.0087 per session on Opus 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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.