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 diagnosegit 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/diagnose)<a href="https://agentmods.dev/skills/donald-ada/workinggenius/diagnose"><img src="https://agentmods.dev/badge/skills/donald-ada/workinggenius/diagnose/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/diagnose"><img src="https://agentmods.dev/badge/skills/donald-ada/workinggenius/diagnose.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 | $0.00070 | $0.00558 |
| Opus 5.5 | $0.00028 | $0.00223 |
| Sonnet 5.5 | $0.00014 | $0.00112 |
| Haiku 4.5 | $0.00007 | $0.00056 |
Grade A, and why
diagnose 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.
What it actually says
Diagnose
A bug is a piece of work whose problem statement nobody confirmed, and debugging fails the way all work fails: at whichever stage got skipped. Read code until a cause feels plausible, fix that, call it done when nothing visibly objects — that is idea straight to implementation at minute scale.
The concept: the six geniuses, run at minute scale — no ceremony, no work file, the same order.
- Wonder — the code confirms the problem. A bug's confirmation is a red reproduction: one command, run here, that shows the symptom — red while the bug lives, green when it dies. Until it exists nothing is confirmed and no theory has standing; catching yourself building one first is the stop. A flaky symptom is confirmed by rate — raise the reproduction until signal beats noise. Then shrink it: cut inputs, config and callers one at a time, re-running after each cut, until everything left is load-bearing. The wrong bug reproduced is the wrong problem confirmed.
- Invention and Discernment — hypotheses are options, and options earn survival. More than one before testing any: a single hypothesis explored is anchoring with extra steps. Each names its prediction — "if this is the cause, that change turns the reproduction green" — because a hypothesis that predicts nothing can only be believed. Attack in rank order, one variable at a time; a dead hypothesis gets its one-line kill-reason, so nobody walks that path twice.
- Enablement and Tenacity — red to green, and green is fresh. The surviving hypothesis becomes a fix proven by the reproduction it was born from, and a regression test at a real seam where one exists. Where none does, that absence is a finding about the design, landed as a seed in
.genius/BACKLOG.mdin BACKLOG-FORMAT's shape, never a license to skip. Close out clean: the rerun fresh, the scaffolding gone, the cause stated where the fix is recorded — a fix whose cause is unstated gets un-fixed by the next confident refactor. What the hunt disproved on the way is corrected where it was written (errataskill).
Three failed fixes impeach the problem statement. Back to Wonder — question the reproduction, and what it silently assumes.
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 e63e9c28201a
- 1mo ago Changed e71bfad87752
- 1mo ago Changed 4642b825106d
- 2mo ago First seen · 17 lines · 70 tokens per session scan A 21e11e21deeb
diagnose is a skill published in the GitHub repository donald-ada/workinggenius (6 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 558 once invoked, about $0.0003 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
c-find-bugs
Use when the user wants concrete defects found in a design, plan, branch, file, or the whole repo.
dw-doctor
Read-only environment diagnostic for a solo-lane repo: whether the tools the hooks and skills assume are installed, and whether the guardrails and the pre-commit really fire here or are silently skipping, each gap reported with a copy-paste fix.
issue
Register a bug, deferral, or known limitation as the next ISS-NNN in docs/registry/ISSUES.md with severity and an investigation path. Use when the user types /genesis:issue, says "log this bug/issue", "defer this", or when work uncovers a problem that will not be fixed in the current task in a GENESIS project.
debugging
Systematic debugging that applies the scientific method to failures. Use when the user says "debug this", "why is this failing", "help me find the bug", or is stuck on a problem and thrashing without progress.
performance
Profiling methodology and optimization strategy for performance work. Use when the user asks to "make this faster", "optimize", "profile", "reduce latency", "fix slow", "improve throughput", or when investigating performance regressions.
sweep
Post-op check for artifacts, damage, and stale references after agent work.