agentmods.dev

aidog CLAUDE.md

aidog CLAUDE.md is an instructions file for coding agents from AIAIDo/aidog. It costs 441 tokens per session, scanned A, original, MIT.

A set of project instructions for aidog, a dashboard for viewing coding-agent sessions, costs, performance, security, and governance. It includes commands for building its React web interface and restarting its server.

In plain words
What is it for?
Use it when modifying aidog's server or React dashboard, rebuilding the web interface, restarting the service, or checking its logs and stored session data.
Why use it?
Changes to the web source do not appear in the dashboard until the built files are regenerated, and server changes require a restart. The instructions document the project layout and the commands needed during development.

Instructions file

not rated 2 5mo ago A scan 441 tokens original MIT
View the source file AIAIDo/aidog
Install

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.

agentmods
npx agentmods add instructions/aiaido/aidog/claude-md
Clone the repo
git clone --depth 1 https://github.com/AIAIDo/aidog

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 aidog CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/aiaido/aidog/claude-md.svg)](https://agentmods.dev/instructions/aiaido/aidog/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/aiaido/aidog/claude-md"><img src="https://agentmods.dev/badge/instructions/aiaido/aidog/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 441 This file is loaded in full into every session.
When invoked 441 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00441 $0.00441
Opus 5 $0.00220 $0.00220
Sonnet 5 $0.00088 $0.00088
Haiku 4.5 $0.00044 $0.00044

Measured 4d ago against content hash 3962e309634a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aidog 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 4d 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.

CLAUDE.md · 48 lines

What it actually says

aidog - ChatOps Toolkit Dashboard

面向所有聊天代理的成本、性能、安全、治理统一守护仪表盘

Quick Commands

Build & Restart Server

# Build frontend (required after modifying src/web/src/**)
npm run build:web

# Kill existing and start fresh (use nohup to prevent process cleanup)
lsof -i :3000 -t | xargs kill -9 2>/dev/null; sleep 1
nohup node bin/aidog.js serve --port 3000 > /tmp/aidog-server.log 2>&1 &
# Check logs: tail -f /tmp/aidog-server.log

Important: Frontend is served from src/web/dist/ (pre-built static files). Any changes to src/web/src/** require npm run build:web to take effect.

Dev Mode

npm run dev

Project Structure

  • bin/aidog.js - CLI entrypoint
  • src/cli/commands/serve.js - aidog serve command (starts web dashboard)
  • src/server/ - Express API server
    • routes/sessions.js - Sessions list & detail APIs
  • src/storage/sqlite.js - SQLite storage layer (better-sqlite3)
  • src/storage/schema.sql - DB schema
  • src/plugins/claude-code/ - Claude Code JSONL parser
  • src/web/src/ - React frontend (Vite)
    • pages/Sessions.jsx - Sessions page
    • components/MessageList.jsx - Message list with sorting

Database

  • Default path: ~/.aidog/data.db
  • Uses better-sqlite3 with WAL mode
  • Main table: token_events (all parsed JSONL events)

Key Notes

  • Claude Code JSONL records are API responses (role: "assistant"). User messages have zero tokens — this is normal, not a bug.
  • Sessions API uses DB-level GROUP BY session_id aggregation for performance.
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. 4d ago First seen · 48 lines · 441 tokens per session scan A 3962e309634a

Subscribe to this mod's changes

aidog CLAUDE.md is an instructions file published in the GitHub repository AIAIDo/aidog (2 stars, last pushed 5mo ago), licensed MIT. It adds 441 tokens to every session, about $0.0022 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 2026-08-31.

Analytics and metricsaiai-agentsaiderchatopsclaude-codecli
Related

Other instructions, from other repositories

bernstein copilot-instructions.md

Copilot instructions for sipyourdrink-ltd/bernstein, covering copilot instructions, architecture, key constraints, before committing and git rules.

sipyourdrink-ltd/bernstein · 740 tokens

yoloai CLAUDE.md

Instructions for kstenerud/yoloai, covering claude code specifics and the quality gate runs itself here.

kstenerud/yoloai · 392 tokens

EGC copilot-instructions.md

Copilot instructions for Fmarzochi/EGC, covering copilot instructions for egc, repository conventions, readme and translations, code review priorities and egc project memory.

Fmarzochi/EGC · 512 tokens

blueclaw AGENTS.md

Instructions for yeomyeonggeori/blueclaw, covering agents.md, core principles, single source of truth, working on this repository and branch names.

yeomyeonggeori/blueclaw · 3,135 tokens

pxx AGENTS.md

AGENTS.md instructions for cdnwetzel/pxx, covering agents.md — working agreements for ai agents in this repo, what this is, commands, hard rules and conventions.

cdnwetzel/pxx · 511 tokens

nanobot CLAUDE.md

Claude Code instructions for HKUDS/nanobot, a project described as: Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps.

HKUDS/nanobot · 5 tokens