ai-agent-session-center: Instructions file for Claude Code

CLAUDE.md

ai-agent-session-center CLAUDE.md is an instructions file for Claude Code, Codex from coding-by-feng/ai-agent-session-center. It costs 14,602 tokens per session, scanned B, original, MIT.

Project instructions for an AI agent session centre: a local dashboard that monitors coding-agent sessions and shows them as interactive 3D characters. It documents the project's technologies, commands, features, and architecture.

In plain words
What is it for?
Working on the dashboard, its server, React interface, desktop app, terminal connections, session hooks, storage, and automated tests.
Why use it?
It gives the coding agent the project context needed to make compatible changes and use the right development and test commands.

Instructions file for Claude CodeCodex

Written for Claude Code and Codex: SessionStart hook event, but also reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is coding-by-feng/ai-agent-session-center's own configuration. It tells Claude Code and Codex how to work on ai-agent-session-center 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 ai-agent-session-center configures →

Reuse

Borrowing it

Nothing to install: this file belongs to coding-by-feng/ai-agent-session-center. 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/coding-by-feng/ai-agent-session-center/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/coding-by-feng/ai-agent-session-center

Made for: Claude Code, Codex.

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 ai-agent-session-center CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/coding-by-feng/ai-agent-session-center/claude-md.svg)](https://agentmods.dev/instructions/coding-by-feng/ai-agent-session-center/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/coding-by-feng/ai-agent-session-center/claude-md"><img src="https://agentmods.dev/badge/instructions/coding-by-feng/ai-agent-session-center/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 14,602 This file is loaded in full into every session.
When invoked 14,602 The same file — it is already loaded in full.
Security scan B 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 $0.14602 $0.14602
Opus 5 $0.07301 $0.07301
Sonnet 5 $0.02920 $0.02920
Haiku 4.5 $0.01460 $0.01460

Measured 8d ago against content hash 20bee3674318, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

ai-agent-session-center CLAUDE.md scanned grade B 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 8d 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.

- **Never modify `~/.claude/settings.json` without atomic write** — write-to-tmp + rename

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **Only `ppid` proves a discovered process is external — never `cwd`.** A dashboard-launched agent fires no hook while it waits at a login/trust prompt, so the 20s scan sees a live pid with a real tty and no owner and l
CLAUDE.md · 261 lines

How it starts

The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Agent Session Center

Localhost dashboard (port 3333) that monitors AI coding agent sessions (Claude Code, Codex) via hooks. Sessions are visualized as 3D robot characters in an interactive cyberdrome. Supports SSH terminals, team/subagent tracking, prompt queuing, workspace snapshots, and session resume.

Tech Stack

Layer Technology
Backend Node.js 18+ (ESM), Express 5, ws 8, tsx
Frontend React 19, Three.js / @react-three/fiber, Zustand 5, Vite 7
Desktop Electron 34, electron-builder 25
Terminal node-pty (IPC in Electron, WebSocket in browser)
Hooks Bash script → JSONL file-based MQ (HTTP POST fallback)
Persistence SQLite / better-sqlite3 (server) + IndexedDB / Dexie (browser)

Commands

npm run dev              # Vite + tsx watch (HMR)
npm run build            # Production build
npm start                # Start production server
npm test                 # Vitest
npm run test:e2e         # Playwright E2E
npm run test:coverage    # Coverage report
npm run typecheck        # tsc --noEmit (src/ only — see Key Invariants)
npm run typecheck:server # tsc --noEmit -p tsconfig.server.json (server/ + src/types)
npm run typecheck:all    # both, in sequence
npm run lint             # ESLint src/
npm run format           # Prettier
npm run electron:dev     # Build + launch Electron app
npm run electron:build   # Build distributable (DMG/NSIS)
npm run install-hooks    # Install hooks into CLI settings
npm run uninstall-hooks  # Remove all dashboard hooks
npm run setup            # Interactive setup wizard
npm run reset            # Remove hooks, clean config, backup

Feature Documentation

All feature logic is documented in docs/feature/. Each doc covers function, purpose, source files, implementation, cross-feature dependencies, and change risks.

MANDATORY WORKFLOW — Before implementing any new feature or modifying an existing one:

  1. Read this CLAUDE.md to identify which feature domain is involved
  2. Read the corresponding feature doc(s) in docs/feature/ to understand the current implementation, source files, dependencies, and change risks
  3. Check the Impact Matrix below to identify connected features that may be affected
  4. Read those connected feature docs too, so you don't introduce regressions
  5. After completing the work, update every feature doc that was affected by the change (via /update-feature-docs)

Read the full file on GitHub · 261 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. 8d ago First seen · 261 lines · 14,602 tokens per session scan B 20bee3674318

Subscribe to this mod's changes

ai-agent-session-center CLAUDE.md is an instructions file published in the GitHub repository coding-by-feng/ai-agent-session-center (82 stars, last pushed 11d ago), licensed MIT. It adds 14,602 tokens to every session, about $0.0730 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

vibe-coding-prompt-template backend.instructions.md

Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.

KhazP/vibe-coding-prompt-template · 139 tokens

vibe-coding-prompt-template tests.instructions.md

Instructions for KhazP/vibe-coding-prompt-template, a project described as: Templates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs.

KhazP/vibe-coding-prompt-template · 116 tokens

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.

openai/codex · 5,153 tokens

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 · 6,785 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 · 7,296 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 · 4,469 tokens