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 skills add donald-ada/workinggenius --skill geniusgit 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/skills/donald-ada/workinggenius/genius)<a href="https://agentmods.dev/skills/donald-ada/workinggenius/genius"><img src="https://agentmods.dev/badge/skills/donald-ada/workinggenius/genius/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.
<a href="https://agentmods.dev/skills/donald-ada/workinggenius/genius"><img src="https://agentmods.dev/badge/skills/donald-ada/workinggenius/genius.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00030 | $0.01352 |
| Opus 5.5 | $0.00012 | $0.00541 |
| Sonnet 5.5 | $0.00006 | $0.00270 |
| Haiku 4.5 | $0.00003 | $0.00135 |
Grade A, and why
genius 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 1mo 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Genius Map
The map answers three questions: where every piece of work stands, what runs next, and which genius went missing when something feels wrong. It routes; it never builds.
The flow
Every piece of work travels through six geniuses, in three pairs:
| Stage | Genius | Command | Skipping it looks like |
|---|---|---|---|
| Ideation | Wonder — question the work | /wonder |
building exactly the wrong thing |
| Invention — generate options | runs inside /discern |
anchoring on the first idea | |
| Activation | Discernment — judge and choose | /discern |
plausible-but-wrong ships |
| Galvanizing — mobilize into slices | /galvanize |
a plan nobody can start | |
| Implementation | Enablement — build with tight loops | /enable |
flying blind until a big-bang reveal |
| Tenacity — finish with evidence | /tenacity |
"done" that isn't |
State lives in .genius/<slug>/<slug>.md — the bounded snapshot a cold session reads whole — with its history in a log shaped as a tree (<slug>.log.md, one branch per stage or slice under log/) and what binds the unbuilt slices in CONTRACT.md, beside it (the genius-file skill owns the discipline). Each stage ends when its one threshold is honestly true; each is a command the user types — Invention excepted, which runs inside /discern because nothing in it waits on the user — and one they don't type simply doesn't run — its absent section is the record. Four layers run underneath: the domain-glossary skill keeps the shared language in CONTEXT.md, the decision-record skill keeps the index of settled decisions in .genius/DECIDED.md, the blindspot skill hunts the unknowns the stages can't reach, and the errata skill corrects what any of them got wrong.
What to do when invoked
The counts first, taken as this command was invoked: the block below is replaced by the instrument's output before you read it, and where a policy notice shows instead (shell injection disabled), run it before saying a number, because a number said without one is a guess:
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.
- 1mo ago Changed · +11 lines a61f678f9fb1
- 1mo ago Changed bfe3df125f9f
- 1mo ago Changed 97edd6fe5c8e
- 1mo ago Changed · +9 lines 811e933431c9
- 2mo ago Changed 5eaec40659fa
- 2mo ago First seen · 38 lines · 30 tokens per session scan A 3bf619b66500
genius is a skill published in the GitHub repository donald-ada/workinggenius (6 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 1,352 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
daily-working
End-to-end pipeline: pull a task from the project's task tracker by ID (Redmine or GitHub Issues today, more addable via a new adapter), sanity-check and impact-assess it against the codebase before touching anything, implement it with the Claude CLI, verify the result in a real browser via the Claude Chrome extension…
tasknotes
This skill should be used when the user asks to 'create a task', 'add a TODO', 'plan a sprint', 'organize tasks', 'track time', 'setup Kanban', 'create task from code', 'sync tasks with sprint', 'pomodoro session', 'start pomodoro', 'time estimate', or mentions TaskNotes, task management, or project planning in…
work
Dispatch a tracker ticket into an isolated worktree and drive it autonomously to an open pull request, then stop for review. Pass interactive to brainstorm the ticket with a human before planning it, or a sentence of editorial direction as a rider. Use when asked to work a ticket end-to-end.
batch
Dispatch a night's batch of Todo tickets — one worktree and one pull request each — and leave a morning summary. Run explicitly; never inferred.
prep
Spec a ticket before it is dispatched. Brainstorms it, decides everything it can recommend an answer for, asks a present human about the little that survives, and leaves the spec, the decisions and anything still open as one ticket comment. No worktree, no branch, no pull request, and the ticket stays where it was.
dw-prune
Walk .ai/backlog/ and decide every entry out loud: drop what is stale or already done, do what is cheap and unblocked, bundle what ships with a cousin, leave the rest. Explicit-invoke only.