Borrowing it
Nothing to install: this file belongs to levi-qiao/sherlock-claude. 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/levi-qiao/sherlock-claude/master/CLAUDE.mdgit clone --depth 1 https://github.com/levi-qiao/sherlock-claudeWrote 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/levi-qiao/sherlock-claude/claude-md)<a href="https://agentmods.dev/instructions/levi-qiao/sherlock-claude/claude-md"><img src="https://agentmods.dev/badge/instructions/levi-qiao/sherlock-claude/claude-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/levi-qiao/sherlock-claude/claude-md"><img src="https://agentmods.dev/badge/instructions/levi-qiao/sherlock-claude/claude-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 | $0.02041 | $0.02041 |
| Opus 5 | $0.01020 | $0.01020 |
| Sonnet 5 | $0.00408 | $0.00408 |
| Haiku 4.5 | $0.00204 | $0.00204 |
Grade A, and why
sherlock-claude CLAUDE.md scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST http://localhost:8005/api/v1/admin/agents/my_agent_type/reload How it starts
The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code when working in this repository.
Project Overview
AI Agent Platform — Enterprise-grade agent execution platform: FastAPI + SQLAlchemy (repository pattern), SolidJS SPA, Claude Agent SDK, YAML-configured agents, plugin/skill system, async task queue with SSE streaming.
Commands
| Area | Command |
|---|---|
| Backend | ./run_dev.sh · Manual: PYTHONPATH=. uvicorn app.main:app --reload --host 0.0.0.0 --port 8005 |
| Frontend | cd frontend → npm install · npm run dev · npm run build |
| Docker | docker build -t ai-agent-platform . && docker run -p 8005:8005 ai-agent-platform |
Architecture
- Repository pattern: All DB access via repositories;
with get_db() as db:+ repo calls. Key repos:TaskRepository,AgentConfigRepository. - Agents:
agents/*.yaml(YAML-configured, Jinja2 templates). Seeded into DB on startup. 90% of agents are YAML-only (no Python code). - SubAgents:
agents/subagents/*.yaml(context isolation). Auto-discovered, invoked via Agent tool for large data processing. - Plugins/Skills:
plugins/<name>/.claude-plugin/plugin.json+skills/<skill>/SKILL.md. Discovered at startup, injected per agent. - Task queue:
MAX_WORKERSconcurrent asyncio tasks. Lifecycle: pending → processing → completed/failed. SSE stream per task. - SPA:
static/dist/index.htmlserved if built; else Jinja2 fallback attemplates/index.html. Build:cd frontend && npm run build.
⚠️ MANDATORY Development Rules
1. Code Cleanliness
- No commented-out code, dead imports, redundant logic, or TODOs in production code
- One implementation path; no fallbacks to old patterns
- When migrating functionality, delete deprecated files immediately
2. Pyright / LSP Errors — Zero Tolerance
- Fix all Pyright/LSP errors you encounter, including pre-existing ones
- Use
Optional[str]instead ofstr = None; proper None guards before attribute access
3. Database Operations — Repository Pattern Only
- NEVER use manual transactions (
db.begin(),db.commit(),db.rollback()) - NEVER inject
Sessioninto services or routes - ALWAYS use
with get_db() as db:+ repository methods
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.
- 10d ago First seen · 217 lines · 2,041 tokens per session scan A 42b4e95a86ea
sherlock-claude CLAUDE.md is an instructions file published in the GitHub repository levi-qiao/sherlock-claude (6 stars, last pushed 4mo ago), licensed MIT. It adds 2,041 tokens to every session, about $0.0102 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.