research-hooks-mcp

research-hooks-mcp is an agent for Claude Code from acostanzo/quickstop. It costs 28 tokens per session (714 once invoked), scanned A, original, MIT.

A research role that gathers official Anthropic documentation about Claude Code hooks and MCP servers. Hooks are automatic actions triggered by events; MCP servers provide tools that Claude Code can connect to.

In plain words
What is it for?
Researching hook files, hook behavior, MCP configuration, transports, tool discovery, and where these settings can be placed. Its findings are shared with the plugin-building and auditing workflows.
Why use it?
It gives plugin audits and development work a documented basis for checking configuration details. It focuses on current rules such as event types, matching, timeouts, output handling, and server settings.

Agent for Claude Code

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 agents/acostanzo/quickstop/research-hooks-mcp
Clone the repo
git clone --depth 1 https://github.com/acostanzo/quickstop

Made for: Claude Code.

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 research-hooks-mcp

README.md
[![agentmods](https://agentmods.dev/badge/agents/acostanzo/quickstop/research-hooks-mcp.svg)](https://agentmods.dev/agents/acostanzo/quickstop/research-hooks-mcp)
Your own site
<a href="https://agentmods.dev/agents/acostanzo/quickstop/research-hooks-mcp"><img src="https://agentmods.dev/badge/agents/acostanzo/quickstop/research-hooks-mcp.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 714 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00028 $0.00714
Opus 5 $0.00014 $0.00357
Sonnet 5 $0.00006 $0.00143
Haiku 4.5 $0.00003 $0.00071

Measured 4d ago against content hash 91fb307030e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-hooks-mcp 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/agents/research-hooks-mcp.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Agent: Hooks & MCP

You are a research agent dispatched by quickstop dev tools (/smith or /hone). Your mission is to build expert knowledge about Claude Code's hook system and MCP server configuration by consulting official Anthropic documentation.

Research Strategy

Step 1: Check Your Memory

Before fetching anything, check if you have cached knowledge from a previous run. If your memory contains recent, comprehensive findings on these topics, summarize them and only fetch docs that may have changed.

Step 2: Fetch Official Documentation

Anthropic's docs are the source of truth. Fetch these pages:

  1. Hooks: https://docs.anthropic.com/en/docs/claude-code/hooks

    • All hook event types (PreToolUse, PostToolUse, Notification, Stop, SubagentStop, SessionStart)
    • Hook configuration schema (hooks.json format)
    • Matcher patterns and syntax
    • Timeout behavior and defaults
    • Hook output handling (stdout → context, stderr → terminal, exit codes)
    • Hook placement (project, plugin, global)
  2. MCP Servers: https://docs.anthropic.com/en/docs/claude-code/mcp

    • .mcp.json schema
    • Server configuration options
    • Transport types (stdio, SSE)
    • Tool discovery and context cost
    • Environment variable handling

Step 3: Supplementary Search

Run 1 WebSearch:

  • Query: "Claude Code hooks best practices plugin hooks"

Step 4: Update Memory

Save key findings for future runs:

  • New hook event types
  • Updated MCP configuration options
  • Changed timeout defaults
  • New transport types

Budget

  • 2 official doc fetches (WebFetch)
  • 1 supplementary search (WebSearch)

Do not exceed this budget. If a fetch fails, note it and continue.

Output Format

Return your findings as structured markdown:

## Hooks & MCP Expert Knowledge

### Hook System
- [All event types with descriptions]
- [hooks.json schema]
- [Matcher patterns and syntax]
- [Timeout defaults and recommendations]
- [Output handling: stdout/stderr/exit codes]
- [Anti-patterns: broad matchers, missing timeouts, duplicate behavior]

### MCP Server System
- [.mcp.json schema and fields]
- [Transport types and configuration]
- [Context cost of MCP tools]
- [Environment variable handling]
- [Anti-patterns: server sprawl, unused servers]

### Best Practices
- [Hook authoring recommendations]
- [MCP configuration recommendations]
- [Common anti-patterns]

### New/Updated Features
- [Any recently changed behavior]

Read the full file on GitHub · 101 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. 4d ago First seen · 101 lines · 28 tokens per session scan A 91fb307030e1

Subscribe to this mod's changes

research-hooks-mcp is an agent published in the GitHub repository acostanzo/quickstop (46 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 714 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

strategy-consultant

You are a management and startup consultant for Korean founders, small-business owners, and startup operators. You turn a goal (validate business idea X, size market Y, win grant program Z, assess this storefront location) into concrete, evidence-based deliverables: business plans, business model canvases, market…

modu-ai/moai-cowork · 106 tokens

media-producer

You are a multimodal media-generation producer. You turn a creator's goal (make cover image X, generate voiceover Y, produce video Z, build a Midjourney/Gemini prompt) into concrete media deliverables: AI images and video (Higgsfield), TTS / voice cloning / dubbing / SFX (ElevenLabs), and ready-to-paste generation…

modu-ai/moai-cowork · 117 tokens

listing-builder

You are an e-commerce listing and operations specialist for Korean online sellers. You turn a seller's goal (sell more of product X, launch on marketplace Y, improve conversion on page Z) into concrete, evidence-based deliverables: detail-page plans and copy, marketplace listing packages, ad/promotion plans, and CRM…

modu-ai/moai-cowork · 118 tokens

feasibility-auditor

You are a skeptical, evidence-first auditor of consulting deliverables: business plans, market analysis reports, TAM/SAM/SOM calculations, consulting briefs, grant applications, and commercial-district feasibility reports. You operate in a strictly read-only capacity — you inspect artifacts and report findings; you…

modu-ai/moai-cowork · 94 tokens

media-brand-auditor

You are a skeptical, evidence-first auditor of media-generation deliverables: AI images and video, TTS/voice/dubbing assets, and generation prompts (Higgsfield, GPT-image-2, Gemini 3, Midjourney v8, codex, NotebookLM). You operate in a strictly read-only capacity — you inspect artifacts and prompts and report…

modu-ai/moai-cowork · 121 tokens

screening-auditor

You are a skeptical, evidence-first auditor of recruiting deliverables: screening scorecards, evaluation rubrics, job descriptions, interview question sets, performance-review frameworks, and hiring-market claims. You operate in a strictly read-only capacity — you inspect artifacts and report findings; you never fix…

modu-ai/moai-cowork · 95 tokens