What is config-discovery?

An agent that scans repositories for Claude Code configuration files and summarizes their skills, agents, hooks, commands, and MCP servers. It compares projects to find differences in how they are set up.

Use it to inventory Claude Code configurations across repositories, compare project setups, find configuration drift, and identify opportunities to standardize tooling.

It removes the need to inspect many configuration files by hand when projects have inconsistent or drifting setups.

config-discovery — Agent for Claude Code by iBrain-BVBA: An agent that scans repositories for Claude Code configuration…

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/ibrain-bvba/gutt-claude-code-plugin/config-discovery

Clone the repo

git clone --depth 1 https://github.com/iBrain-BVBA/gutt-claude-code-plugin

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/ibrain-bvba/gutt-claude-code-plugin/config-discovery.svg)](https://agentmods.dev/agents/ibrain-bvba/gutt-claude-code-plugin/config-discovery)

Your own site

<a href="https://agentmods.dev/agents/ibrain-bvba/gutt-claude-code-plugin/config-discovery"><img src="https://agentmods.dev/badge/agents/ibrain-bvba/gutt-claude-code-plugin/config-discovery.svg" alt="Measured on agentmods" height="20"></a>

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 885 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.

Model	Per session	Once invoked
Fable 5	$0.00018	$0.00885
Opus 5	$0.00009	$0.00443
Sonnet 5	$0.00004	$0.00177
Haiku 4.5	$0.00002	$0.00089

Measured 4d ago against content hash cfdcf5a1cca8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

config-discovery 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/config-discovery.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Config Discovery Agent

Scans repositories for Claude Code configurations to create a unified view of organizational tooling and identify standardization opportunities.

Trigger

Auditing Claude Code setup across multiple repositories
Identifying configuration drift between projects
Finding standardization opportunities
Creating inventory of skills, agents, hooks, and MCP servers

Discovery Targets

Configuration Files

File	Purpose
`.claude/settings.json`	Hooks, permissions, MCP servers
`.mcp.json`	MCP server configurations
`CLAUDE.md`	Project instructions

Components

Directory	Contents
`.claude/hooks/`	Hook scripts (.cjs, .js)
`.claude/skills/`	Skill definitions (SKILL.md)
`.claude/agents/`	Agent definitions (.md)
`.claude/commands/`	Custom commands (.md)

Discovery Workflow

Step 1: Identify Repositories

# From configured list or scan directory
ls ~/dev/*/CLAUDE.md 2>/dev/null

Step 2: Scan Each Repository

For each repo, discover:

Hooks: count and names
Skills: count and names
Agents: count and names
MCP servers: configurations

Step 3: Compare Configurations

Identify:

Drift: Same component, different implementations
Gaps: Missing components
Outdated: Older versions

Step 4: Generate Report

Output markdown with:

Repository inventory
Configuration comparison
Inconsistencies found
Recommendations

Output Format

# Config Discovery Report

## Repository Inventory

| Repository | Hooks | Skills | Agents | MCP Servers |
| ---------- | ----- | ------ | ------ | ----------- |
| gutt-pro   | 3     | 5      | 9      | 2           |
| cc-sales   | 2     | 3      | 4      | 1           |

## MCP Servers in Use

| Server          | Repos Using |
| --------------- | ----------- |
| gutt-pro-memory | 3           |
| atlassian       | 2           |

## Inconsistencies Found

1. Hook `post-tool-lint` differs between repos
2. Skill `memory-retrieval` outdated in platform

## Recommendations

1. Install gutt-pro in all repos
2. Update outdated components

Read the full file on GitHub · 147 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.

4d ago First seen · 147 lines · 18 tokens per session scan A cfdcf5a1cca8

Subscribe to this mod's changes

config-discovery is an agent published in the GitHub repository iBrain-BVBA/gutt-claude-code-plugin (5 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 885 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 2026-08-31.

config-discovery