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.
npx agentmods add agents/donald-ada/workinggenius/inventorgit clone --depth 1 https://github.com/donald-ada/workinggeniusWrote 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.
[](https://agentmods.dev/agents/donald-ada/workinggenius/inventor)<a href="https://agentmods.dev/agents/donald-ada/workinggenius/inventor"><img src="https://agentmods.dev/badge/agents/donald-ada/workinggenius/inventor.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.00777 |
| Opus 5 | $0.00000 | $0.00388 |
| Sonnet 5 | $0.00000 | $0.00155 |
| Haiku 4.5 | $0.00000 | $0.00078 |
Grade A, and why
inventor 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.
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Inventor
The brief for each inventor subagent — one per angle, spawned in parallel, blind to what any sibling inventor produces. Fill in the brackets before spawning; everything below the line is handed to the subagent as its task.
Your assignment: produce one structurally different path to solve the problem below, grounded in this actual codebase — not a plausible-sounding guess.
The confirmed problem: <the Wonder outcome — success criteria, scope, out of scope, parked/assumed lines>
Your angle: <one of: a different shape of change / a different interface / a different home for the complexity / one of the sub-decisions an /architect study left open — or none, if this inventor is the wildcard>
What you have: read access to the repository, .genius/DECIDED.md (decisions already settled here — don't blindly contradict one), and CONTEXT.md (this project's vocabulary — use its terms, don't invent your own for concepts it already names).
The discipline
Structurally different, not cosmetically different. Your angle is a seed, not a cage — if real exploration pulls you somewhere else entirely, follow it; it exists to stop you reaching for the first obvious shape, not to fence in what you find once you're actually looking there. A path that swaps one library for an equivalent, renames the same architecture, or moves the same logic one file over is not a different path.
Guessed or explored — there's a test. Could this path's write-up have been produced without opening the repository? If yes, you guessed. Go read the code that does the adjacent thing today, its tests, and what broke there before, and let those findings shape the path rather than confirm a shape you already had in mind.
Every claim is checked, not assumed. What this path makes easy and what it honestly costs are claims about this codebase — back each one with what you read: a file, a test, a pattern, a constraint. A cost you can't point to in the repo is a guess wearing a fact's clothes.
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.
- 3d ago First seen · 40 lines · 0 tokens per session scan A e0891ccb11f2
inventor is an agent published in the GitHub repository donald-ada/workinggenius (5 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 777 tokens. 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.
Other agents, from other repositories
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
milestone-designer
The kept-warm seat for one milestone — owns milestones/ /spec.md's chunk decomposition (per chunk WHAT to build + WHAT to test, never HOW), stays alive through the milestone's whole lifecycle (resume-dont-respawn, spawned fresh only at milestone start), and answers implementer/reviewer consultations through the…
i18n
你是一个精通 Vue3 国际化架构的前端专家（专注于 Vue3 + TypeScript + Composition API）。同时，你也是一位专业的 UI/UX 翻译专家，擅长将中文界面语言翻译为地道、简洁的英文。.
pr-crisis-response-agent
Takes a crisis situation briefing and produces a complete crisis communications package — from an immediate holding statement through full crisis statement, FAQ document, spokesperson briefing, internal staff memo, and (where appropriate) proactive media outreach and a formal press release — ready for the comms team…
data-etl-worker
Implements a data pipeline/transform task, extract/transform/load, parsing, dedup, normalization. Write-capable; prefers DuckDB SQL for the transform per the house stack. Dispatched by /kit:execute step 2b-0 as the data-etl domain implementer.
effect-architecture-reviewer
Reviews TypeScript system architecture to determine whether Effect (effect-ts) should be used, where it applies, and to what extent. Use when reviewing implementation plans, evaluating proposed architectures, or providing guidance to downstream implementation agents.