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/walterra/eddoapp/claude-mdgit clone --depth 1 https://github.com/walterra/eddoappWrote 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/walterra/eddoapp/claude-md)<a href="https://agentmods.dev/instructions/walterra/eddoapp/claude-md"><img src="https://agentmods.dev/badge/instructions/walterra/eddoapp/claude-md.svg" alt="Measured on agentmods" 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 | $0.10524 | $0.10524 |
| Opus 5 | $0.05262 | $0.05262 |
| Sonnet 5 | $0.02105 | $0.02105 |
| Haiku 4.5 | $0.01052 | $0.01052 |
Grade A, and why
eddoapp 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.
How it starts
The opening of the file, as written. The whole thing — 1,032 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.
Build & Test Commands
Commands to run servers
Never run these commands yourself or kill related processes. The user is responsible for running the server. If you need to run or restart one of these commands, ask the user to do it for you.
- web (client+api):
pnpm dev(port 3000) - web client dev only:
pnpm dev:web-client(port 5173 in dev) - web api dev only:
pnpm dev:web-api(port 3000, passes through web-client) - MCP server dev:
pnpm dev:mcp-server - Telegram bot dev:
pnpm dev:telegram-bot
Root Level
Use these commands for investigating, testing and linting.
DO NOT cd into packages. you MUST stay in root and run commands like pnpm test|build from the repo root.
CRITICAL: Run pnpm check:commit to verify code before requesting a commit.
- IMPORTANT: Use
pnpm logs:tailto investigate unified logs produced bypnpm dev - Build all packages:
pnpm build(always run from the repo root, not from individual package dirs) - Build for production:
pnpm build:production - Lint:
pnpm lint - Format check:
pnpm lint:format - Commit check (required before commit):
pnpm check:commit - Format fix:
pnpm format - Unit tests (default):
pnpm test - Unit tests only:
pnpm test:unit - MCP server integration tests:
pnpm test:integration:mcp-server(uses vitest with global setup) - Agent loop integration tests:
pnpm test:integration:agent-loop(uses VCR caching, see below) - Agent loop tests (record):
pnpm test:integration:agent-loop:record(re-record cassettes) - Agent loop tests (playback):
pnpm test:integration:agent-loop:playback(CI mode, no API calls) - E2E tests:
pnpm test:e2e - Full test suite:
pnpm test:all - CI test suite:
pnpm test:ci(excludes telegram-bot integration tests) - CI test suite with all tests:
pnpm test:ci:all(requires ANTHROPIC_API_KEY) - Run single test:
pnpm vitest:run src/path/to/file.test.ts - TypeScript check:
pnpm tsc:check - MCP server test:
pnpm test:mcp-server(this lets you run commands against mcp-server) - Check unused dependencies:
pnpm knip
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.
- 4d ago First seen · 1,032 lines · 10,524 tokens per session scan A 0f472ccb6a02
eddoapp CLAUDE.md is an instructions file published in the GitHub repository walterra/eddoapp (58 stars, last pushed 2d ago), licensed Apache-2.0. It adds 10,524 tokens to every session, about $0.0526 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
paceflow CLAUDE.md
Instructions for paceaitian/paceflow, covering claude.md, 维护规则, 常用验证, 一条命令聚合全部核心套件 + claude plugin validate + git diff --check and 任一子套件非零退出即整体非零退出，杜绝手敲漏跑某套件致回归静默漏网.
agent-context-system AGENTS.md
Instructions for AndreaGriffiths11/agent-context-system, covering agents.md, project, commands, architecture and project knowledge (compressed).
KDD AGENTS.md
AGENTS.md instructions for MauricioPerera/KDD: Este repositorio usa la metodología KDD (Knowledge-Driven Development). Las reglas obligatorias completas están en .agents/AGENTS.md y la skill local en .agents/skills/kdd-okf-ccdd-hybrid/SKILL.md.
lumen AGENTS.md
AGENTS.md instructions for ory/lumen, covering agents.md, repository expectations and commands.
ai-auto-work CLAUDE.md
Claude Code instructions for chaohong-ai/ai-auto-work, covering gamemaker - ai native 游戏创作平台, 项目简介, ai 工作目录约定 and 按需加载（不默认装载）.
catalyst AGENTS.md
AGENTS.md instructions for coalesce-labs/catalyst, covering agents.md, what this repository is, agent philosophy, build & test and key principles.