agentmods.dev

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.

In plain words
What is it for?
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.
Why use it?
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.

Instructions file for CodexOpenCode

49 2d ago C scan 417 tokens original MIT
View the source file pacphi/agentic-kit
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/pacphi/agentic-kit/agents-md
Clone the repo
git clone --depth 1 https://github.com/pacphi/agentic-kit

Made for: Codex, OpenCode.

Per session 417 This file is loaded in full into every session.
When invoked 417 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.00417 $0.00417
Opus 5 $0.00209 $0.00209
Sonnet 5 $0.00083 $0.00083
Haiku 4.5 $0.00042 $0.00042

Measured 2d ago against content hash 902e5218a96f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

agentic-kit AGENTS.md scanned grade C 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 2d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- Codex-side project instructions (mirror of CLAUDE.md). Full ruflo + agentic-qe operating guidance lives machine-wide at ~/.codex/AGENTS.md / ~/.claude/CLAUDE.md. -->
AGENTS.md · 41 lines

What it actually says

Ruflo Machine Ref (Codex / AGENTS.md)

This repo (@pacphi/agentic-kit) is a plain-ESM Node.js CLI — zero runtime dependencies; only bin/, src/, and claude/ ship. Tooling (eslint, tsc --checkJs, markdownlint, lychee) is devDependencies only. Codex reads this file the way Claude Code reads CLAUDE.md; keep the two in sync.

Swarm Config

  • Topology: hierarchical-mesh (anti-drift)
  • Max Agents: 15
  • Memory: hybrid
  • HNSW: Enabled
  • Neural: Enabled
ruflo swarm init --topology hierarchical --max-agents 15 --strategy specialized

Build & Test

pnpm test          # node --test unit suite + statusline segments
pnpm run check     # typecheck + lint + markdown lint + build + test
pnpm run build     # packaging + CLI-load validation (no transpile — plain ESM)

Operating rules

  • Do what's asked; nothing more. Prefer editing existing files over new ones.
  • Never commit secrets or .env files. Never auto-commit/push without an explicit ask.
  • No Co-Authored-By trailer unless .claude/settings.json sets attribution.commit.
  • Keep files under ~500 lines; validate input at boundaries.

Agentic QE v3

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. 2d 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 (49 stars, last pushed 2d ago), licensed MIT. It adds 417 tokens to every session, about $0.0021 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

LanguagesTestingWriting and docsanthropicclaudeclaude-codedeveloper-toolsmcpnodejs
Related

Other instructions, from other repositories

featurevisor AGENTS.md

Instructions for featurevisor/featurevisor, covering links, stack, packages, examples and installation.

featurevisor/featurevisor · 666 tokens

platform AGENTS.md

Instructions for doka-guide/platform, covering agents.md — как работать с платформой доки, 1. правила работы, сначала подумай, потом пиши, минимум кода and правки хирургические.

doka-guide/platform · 2,815 tokens

claude-code-statusline AGENTS.md

Instructions for ilia-pluzhnikov/claude-code-statusline, covering claude-code-statusline, project shape, rules for contributors (and ai agents), editing this file and testing.

ilia-pluzhnikov/claude-code-statusline · 1,089 tokens

zapo CLAUDE.md

Instructions for vinikjkkj/zapo: The contributor handbook for this repository lives in AGENTS.md. Read that file and follow it as your primary source of project conventions, architecture rules, performance constraints, and review anti-patterns.

vinikjkkj/zapo · 152 tokens

lib.reviews AGENTS.md

Instructions for permacommons/lib.reviews, covering lib.reviews agent notes, tech stack and guidance for agents.

permacommons/lib.reviews · 365 tokens

Silex AGENTS.md

AGENTS.md instructions for silexlabs/Silex, covering agents.md, tech stack, run it locally, building the desktop app and when writing code for silex (editing source).

silexlabs/Silex · 1,155 tokens