agentmods.dev

agentctl AGENTS.md

Project instructions for AgentCtl, a TypeScript command-line tool that keeps one shared configuration for several coding-agent runtimes. It generates settings for Claude Code, Codex CLI, OpenCode, and Kiro.

In plain words
What is it for?
Use it to initialize, synchronize, validate, compare, or inspect agent configuration across supported runtimes.
Why use it?
It avoids maintaining separate permission and runtime settings for each coding-agent tool.

Instructions file for CodexOpenCode

2 3d ago A scan 1,100 tokens original Apache-2.0
View the source file itslab42/agentctl
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 instructions/itslab42/agentctl/agents-md
Clone the repo
git clone --depth 1 https://github.com/itslab42/agentctl

Made for: Codex, OpenCode.

Per session 1,100 This file is loaded in full into every session.
When invoked 1,100 The same file — it is already loaded in full.
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 $0.01100 $0.01100
Opus 5 $0.00550 $0.00550
Sonnet 5 $0.00220 $0.00220
Haiku 4.5 $0.00110 $0.00110

Measured yesterday against content hash 30f535aff0fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentctl AGENTS.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 yesterday.

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.

AGENTS.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentCtl

Single source of truth for AI coding-agent configuration. Keeps a runtime-neutral .ai/ directory and generates settings for Claude Code, Codex CLI, OpenCode, and Kiro.

Project Overview

  • Package: @lab42/agentctl (npm, Apache-2.0)
  • Language: TypeScript (CommonJS output)
  • Runtime: Node.js ≥ 18
  • Package manager: pnpm 11+
  • Test runner: Node.js built-in test runner (node --test) — NOT Vitest
  • Linter/Formatter: OXLint + OxFmt (not ESLint/Prettier)
  • Build: tsc → dist/, stubs copy, then oxc-minify

Architecture

.ai/config.yaml          ← source of truth (runtimes, project name, settings)
.ai/permissions.yaml     ← runtime-neutral permissions (deny_over_allow)
src/config.ts            ← parses & validates config.yaml
src/permissions.ts       ← parses & validates permissions.yaml
src/cli.ts              ← CLI entry point (init, sync, check, validate, diff, status)
src/adapters/claude.ts   ← renders .claude/settings.json
src/adapters/codex.ts    ← renders .codex/config.toml + hooks/permission-policy.py
src/adapters/opencode.ts ← renders .opencode/opencode.json
src/adapters/kiro.ts     ← renders .kiro/settings/permissions.yaml
  • Config flows one direction: .ai/ → adapters → generated files.
  • Generated files are never read back as input.
  • Permissions use deny_over_allow precedence exclusively.

Important Rules

  • You must not downgrade a package just because it solves a problem.
  • Always use top-level gh and pnpm commands such as gh view <id> wherever possible.
  • If a top-level command is available, then avoid using sub-commands such as gh run <sub_command> or pnpm run <sub_command>.
  • Never edit generated files (.claude/, .codex/, .opencode/, .kiro/settings/permissions.yaml) directly — edit the .ai/ source then run agentctl sync.
  • Adapters must remain pure functions: take Permissions (and optional settings), return a string. No I/O.

CLI Commands

agentctl init      # scaffold .ai/ directory
agentctl validate  # check .ai/ files parse correctly
agentctl sync      # generate all enabled runtime configs
agentctl check     # report drift (exit 1 if out of sync)
agentctl diff      # unified diff of pending changes
agentctl status    # one-line sync summary per runtime (exit 1 if drift)
agentctl --version # print version

Read the full file on GitHub · 96 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. yesterday First seen · 96 lines · 1,100 tokens per session scan A 30f535aff0fc

Subscribe to this mod's changes

agentctl AGENTS.md is an instructions file published in the GitHub repository itslab42/agentctl (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,100 tokens to every session, about $0.0055 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.

LanguagesPlanningai-agentclaudeclaude-codeclicodexcursor
Related

Other instructions, from other repositories

awesome-copilot-id AGENTS.md

Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.

GulajavaMinistudio/awesome-copilot-id · 7,686 tokens

hiveshare CLAUDE.md

Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.

KB-perByte/hiveshare · 1,301 tokens

llm-safe-haven CLAUDE.md

Instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.

pleasedodisturb/llm-safe-haven · 1,322 tokens

kleosrules AGENTS.md

Instructions for kleosr/kleosrules, a project described as: Cursor harness pack: user rules, skills, Bash hooks, local HANDOFF memory. macOS, Linux, Windows (WSL).

kleosr/kleosrules · 417 tokens

coding-agent-safety-gate AGENTS.md

Instructions for ASER-ho/coding-agent-safety-gate, covering agents / 代理规则, 仓库类型 / repository type and ai 代理规则 / rules for ai coding agents.

ASER-ho/coding-agent-safety-gate · 589 tokens

yapcap CLAUDE.md

Claude Code instructions for TopiCsarno/yapcap, a project described as: Native COSMIC panel applet showing local usage limits for Codex, Claude Code, and Cursor.

TopiCsarno/yapcap · 3 tokens