What is agentctl CLAUDE.md?

Development instructions for agentctl, a command-line tool that synchronizes settings such as servers, prompts, rules, and skills across several coding-agent tools.

Use them when developing agentctl, running its Go tests, updating expected test outputs, building the command-line program, or checking configurations.

They explain the project structure and the commands needed to build, test, validate, and diagnose changes, reducing guesswork during development.

How iheanyi/agentctl configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to iheanyi/agentctl. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/iheanyi/agentctl/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/iheanyi/agentctl

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/instructions/iheanyi/agentctl/claude-md/github.svg)](https://agentmods.dev/instructions/iheanyi/agentctl/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/iheanyi/agentctl/claude-md"><img src="https://agentmods.dev/badge/instructions/iheanyi/agentctl/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/iheanyi/agentctl/claude-md"><img src="https://agentmods.dev/badge/instructions/iheanyi/agentctl/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,996 This file is loaded in full into every session.

When invoked 1,996 The same file — it is already loaded in full.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.01996	$0.01996
Opus 5.5	$0.00798	$0.00798
Sonnet 5.5	$0.00399	$0.00399
Haiku 4.5	$0.00200	$0.00200

Measured 2mo ago against content hash a2fe986280c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

agentctl CLAUDE.md scanned grade B 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 2mo 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

| Claude Code | `~/.claude/settings.json` | `mcpServers` |

CLAUDE.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - agentctl Development Guide

Project Overview

agentctl is a universal agent configuration manager for syncing MCP servers, commands, rules, prompts, and skills across 10 agentic tools: Claude Code, Claude Desktop, Cursor, Codex, OpenCode, Cline, Windsurf, Zed, Continue, and Gemini.

Module: github.com/iheanyi/agentctl

Quick Commands

# Build
go build ./...

# Run all tests
go test ./...

# Run golden tests only
go test ./pkg/sync/... -run Golden -v

# Update golden files
UPDATE_GOLDENS=1 go test ./pkg/sync/... -run Golden

# Interactive golden updates
GOLDEN_INTERACTIVE=1 go test ./pkg/sync/... -run Golden

# Build binary
go build -o agentctl ./cmd/agentctl

# Run CLI
./agentctl --help
./agentctl add filesystem
./agentctl sync --dry-run
./agentctl validate
./agentctl doctor -v

Architecture

Package Structure

cmd/agentctl/       # Entry point
internal/
├── cli/            # Cobra commands (add, sync, validate, doctor, etc.)
├── tui/            # Bubble Tea TUI
pkg/
├── mcp/            # MCP server types (Server, Source, Transport)
├── config/         # Config loading/saving, profiles, project-local
├── sync/           # Tool adapters + golden test infrastructure
│   ├── adapter.go      # Adapter interface and registry
│   ├── claude.go       # Claude Code adapter
│   ├── cursor.go       # Cursor adapter (filters HTTP/SSE)
│   ├── opencode.go     # OpenCode adapter (uses state file)
│   ├── state.go        # External state file for tracking
│   ├── golden_test.go  # Comprehensive golden tests
│   └── testdata/       # Fixtures and golden files
├── aliases/        # Bundled + user aliases
├── builder/        # Git cloning, auto-build detection
├── profile/        # Profile CRUD
├── registry/       # mcp.so API client
├── output/         # Terminal output formatting
├── command/        # Slash command schema
├── rule/           # Rules with YAML frontmatter
├── prompt/         # Prompt templates
├── skill/          # Directory-based skills
├── secrets/        # Keychain integration
├── lockfile/       # Version locking

Read the full file on GitHub · 252 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.

2mo ago First seen · 252 lines · 1,996 tokens per session scan B a2fe986280c3

Subscribe to this mod's changes

agentctl CLAUDE.md is an instructions file published in the GitHub repository iheanyi/agentctl (20 stars, last pushed 9mo ago), licensed MIT. It adds 1,996 tokens to every session, about $0.0080 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

agentctl CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agentctl CLAUDE.mdiheanyi/agentctl	Instructions file	20	9mo ago	MIT	B	1,996	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	279k	today	MIT	A	4,325	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot

agentctl: Instructions file for Claude Code