What is agentic-kit AGENTS.md?

Repository instructions for agentic-kit, a JavaScript command-line tool that coordinates coding agents. They define its structure, swarm setup, checks, and operating rules.

Use them when changing the agentic-kit source, command-line behavior, swarm configuration, or documentation. They identify the commands for testing, checking, and building the project.

They help an agent follow the repository's build and test process, respect its multi-agent configuration, and avoid unsafe changes such as committing secrets or pushing automatically.

How pacphi/agentic-kit configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to pacphi/agentic-kit. 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/pacphi/agentic-kit/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/pacphi/agentic-kit

Made for: Codex, OpenCode.

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/pacphi/agentic-kit/agents-md/github.svg)](https://agentmods.dev/instructions/pacphi/agentic-kit/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/pacphi/agentic-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/pacphi/agentic-kit/agents-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/pacphi/agentic-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/pacphi/agentic-kit/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,484 This file is loaded in full into every session.

When invoked 4,484 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	$0.04484	$0.04484
Opus 5.5	$0.01794	$0.01794
Sonnet 5.5	$0.00897	$0.00897
Haiku 4.5	$0.00448	$0.00448

Measured 23d ago against content hash a99fac109179, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

agentic-kit AGENTS.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 23d 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.

Windows), `~/.claude/CLAUDE.md`, `~/.claude/settings.json`, `~/.claude.json`,

AGENTS.md · 534 lines

How it starts

The opening of the file, as written. The whole thing — 534 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agentic-kit

Setup, repair, evidence reporting, and supervised execution for coding-agent integrations

Project Overview

A cross-platform, zero-runtime-dependency Node.js CLI (ak / agentic-kit) integrating Ruflo, Agentic QE, Claude Code, Codex, and opt-in OpenCode.

Tech Stack: JavaScript ES modules (.mjs), Node.js 22+, TypeScript checking via tsc Architecture: Domain-Driven Design with bounded contexts

Documentation layout

Plans go to docs/plans/YYYY-MM-DD-<feature>.md and specs to docs/plans/YYYY-MM-DD-<topic>-design.md, including the ones Superpowers writes. Never create docs/superpowers/ or any other folder under docs/.
Finished plans and specs move to docs/archive/ in the pull request that completes the work, using node scripts/docs-relocate.mjs, with one index row per file in docs/archive/README.md.
Dated audits and evidence go straight to docs/archive/; dormant proposals to docs/proposals/.
Top-level docs/*.md files are living guides, each listed in docs/README.md.
Markdown file names are lower case. Only README.md, CLAUDE.md, AGENTS.md, and SKILL.md keep capitals. Never move an ADR.

Quick Start

Installation

pnpm install

Build

npm run build

Test

npm test

Development

Source runs directly; there is no dev script or compilation step.

node bin/agentic-kit.mjs --help --all
pnpm run typecheck

Agent Coordination

Swarm Configuration

For complex work, the preferred coordination shape is hierarchical. These are workflow preferences, not evidence that a swarm is running; obey the current host/session capability and concurrency limits:

Setting	Value	Purpose
Topology	`hierarchical`	Queen-led coordination (anti-drift)
Max Agents	8	Optimal team size
Strategy	`specialized`	Clear role boundaries
Consensus	`raft`	Leader-based consistency

Read the full file on GitHub · 534 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.

23d ago Changed · +2 lines · +37 tokens per session a99fac109179
28d ago Changed · +14 lines · +238 tokens per session 191eccb06a10
29d ago Changed · +39 lines · +437 tokens per session e2ae17d5a0ea
1mo ago Changed · +20 lines · +505 tokens per session scan A → B 7378592c8db0
1mo ago Changed · -30 lines · -159 tokens per session c48fac7a43b6
1mo ago Changed · +448 lines · +3,009 tokens per session scan C → A 2c870da6ee9b
1mo ago First seen · 41 lines · 417 tokens per session scan C 902e5218a96f

Subscribe to this mod's changes

agentic-kit AGENTS.md is an instructions file published in the GitHub repository pacphi/agentic-kit (61 stars, last pushed yesterday), licensed MIT. It adds 4,484 tokens to every session, about $0.0179 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.

Building agents Claude Code anthropic claude developer-tools mcp nodejs

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).

microsoft/vscode · 9,715 tokens

agentic-kit: Instructions file for Codex