workinggenius AGENTS.md

workinggenius AGENTS.md is an instructions file for Codex, OpenCode from donald-ada/workinggenius. It costs 221 tokens per session, scanned A, original, MIT.

Repository instructions for the Working Genius plugin, which distributes reusable agent skills through a marketplace and command-line installer.

In plain words
What is it for?
Use them when editing skills, preparing releases, or changing the plugin marketplace contents.
Why use it?
They keep releases and project conventions consistent, including version updates when the skills change.

Instructions file for CodexOpenCode

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/donald-ada/workinggenius/agents-md
Clone the repo
git clone --depth 1 https://github.com/donald-ada/workinggenius

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.

agentmods badge for workinggenius AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/donald-ada/workinggenius/agents-md.svg)](https://agentmods.dev/instructions/donald-ada/workinggenius/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/donald-ada/workinggenius/agents-md"><img src="https://agentmods.dev/badge/instructions/donald-ada/workinggenius/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 221 This file is loaded in full into every session.
When invoked 221 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 $0.00221 $0.00221
Opus 5 $0.00111 $0.00111
Sonnet 5 $0.00044 $0.00044
Haiku 4.5 $0.00022 $0.00022

Measured 3d ago against content hash 334cf81c0756, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workinggenius 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 3d 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.

AGENTS.md · 14 lines

What it actually says

Working Genius — repository instructions

This repository is the Working Genius plugin itself: the Agent Skills under skills/, distributed through the Claude Code plugin marketplace and the skills CLI.

Releasing

Any change under skills/ or .claude-plugin/ that merges to main bumps version in .claude-plugin/plugin.json in the same PR. Marketplace clients detect updates only through that version — a merge without a bump ships behavior no installer can pull. If skills/ gained or lost a skill, the count in README.md's install line moves with it.

Conventions

  • Skills are prose, and the repo stays that way: no runtime, no scripts, no state a fork can't carry.
  • Every rule a skill states carries its why; a constraint that can't name its reason doesn't land.
  • Killed designs stay killed unless new evidence reopens them. Before proposing express paths, sizing calls, autonomy modes, gate checklists, or skip bookkeeping, read the git history — each was removed by a recorded ruling that names its kill-reason.
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. 3d ago First seen · 14 lines · 221 tokens per session scan A 334cf81c0756

Subscribe to this mod's changes

workinggenius AGENTS.md is an instructions file published in the GitHub repository donald-ada/workinggenius (5 stars, last pushed 6d ago), licensed MIT. It adds 221 tokens to every session, about $0.0011 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.