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 megamen32/LastHumanCommit --skill focus-groupsgit clone --depth 1 https://github.com/megamen32/LastHumanCommitWrote 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/megamen32/lasthumancommit/focus-groups)<a href="https://agentmods.dev/skills/megamen32/lasthumancommit/focus-groups"><img src="https://agentmods.dev/badge/skills/megamen32/lasthumancommit/focus-groups/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/megamen32/lasthumancommit/focus-groups"><img src="https://agentmods.dev/badge/skills/megamen32/lasthumancommit/focus-groups.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 | $0.00034 | $0.00823 |
| Opus 5.5 | $0.00014 | $0.00329 |
| Sonnet 5.5 | $0.00007 | $0.00165 |
| Haiku 4.5 | $0.00003 | $0.00082 |
Grade A, and why
focus-groups 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 yesterday.
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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomous focus groups
Use fresh Zero Knowledge groups for major milestone acceptance and the final acceptance of that work, roughly 3 hours of coherent implementation per tangible outcome, not every hour or small change. Normal TDD and technical checks remain continuous. Three hours is a planning scale, not a forced delay or a rigid timer. A milestone must already name a user, a realistic goal, a before/after difference and a result that can actually be tried. No observable outcome means re-anchor the work, not spend another round on hashes and waiting for unrelated sessions.
Form a useful group
Lead creates varied plausible personas with a name, age, personality, experience, realistic goal, device, constraints and expectations. Use random variation within the actual audience instead of choosing only users likely to succeed. Do not stereotype competence from age or any demographic trait: describe experience and conditions explicitly. Names and fictional biographies alone do not create diversity. Personality should change how they try to solve the task (for example impatient, methodical or exploratory), not impose a predetermined positive/negative verdict. Example goals: get a first successful result with no product experience; import existing work; resume a long operation after leaving; correct a mistaken input on a phone. Do not give the exact intended solution path.
Choose multiple distinct users based on coverage and the value of additional evidence; no universal fixed count. Do not cut useful feedback merely because independent testing is expensive. More meaningful observations are welcome, but random complaint volume and longer biographies are not the goal. Use strong-enough tool operators even for novice personas. Model diversity and persona diversity are separate dimensions; do not claim one provides the other.
Give each Tester a fresh session, isolated browser/device profile when needed,
suitable test identity/data and a fixed product revision. Run compatible lanes
in parallel. Testers do not see implementation or one another's findings before
their independent first attempt. Apply ../user-testing/SKILL.md.
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.
- yesterday Changed · +17 lines 3e657f8d5a6c
- 1mo ago First seen · 55 lines · 34 tokens per session scan A a8d977a360f5
focus-groups is a skill published in the GitHub repository megamen32/LastHumanCommit (2 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 823 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 2026-09-05.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…