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 GuitarAlchemist/ga --skill ga-chatbot-afk-harnessgit clone --depth 1 https://github.com/GuitarAlchemist/gaWrote 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/guitaralchemist/ga/ga-chatbot-afk-harness)<a href="https://agentmods.dev/skills/guitaralchemist/ga/ga-chatbot-afk-harness"><img src="https://agentmods.dev/badge/skills/guitaralchemist/ga/ga-chatbot-afk-harness/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/guitaralchemist/ga/ga-chatbot-afk-harness"><img src="https://agentmods.dev/badge/skills/guitaralchemist/ga/ga-chatbot-afk-harness.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 | $0.00111 | $0.02757 |
| Opus 5.5 | $0.00044 | $0.01103 |
| Sonnet 5.5 | $0.00022 | $0.00551 |
| Haiku 4.5 | $0.00011 | $0.00276 |
Grade A, and why
GA Chatbot AFK Harness 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ga-chatbot-afk-harness
The orchestration layer for fully-AFK GA chatbot development + QA. It does NOT reimplement the improvement loop — it wires together pieces that already exist and adds the three things they lacked: a semantic QA signal, live instrumentation for a human dashboard, and one safe "arm and walk away" entry.
┌──────────────────────── this harness ────────────────────────┐
preflight → │ QA snapshot dev cycles QA snapshot │ → exit
│ (det oracle + (/auto-optimize, (re-measure) │
│ semantic panel) Iron Laws + rollback) │
└───────────────── status → dashboard at every step ───────────┘
What it composes (do NOT duplicate these)
| Piece | Role | Owned by |
|---|---|---|
Scripts/run-prompt-corpus.ps1 |
deterministic oracle (pass_pct) |
existing |
/ga-chatbot-qa-panel (workflow) |
semantic judge panel → state/quality/chatbot-qa-semantic/ |
this session |
/auto-optimize |
Level-3 dev loop: pick worst → fix → roundtrip → commit/revert | existing |
/chatbot-qa-roundtrip-validate |
per-commit rollback gate | existing |
state/quality/chatbot-qa/baseline.json |
metric + scope_boundary + caps | existing |
Scripts/afk-harness-status.ps1 |
instrumentation writer → dashboard | this session |
Tools/afk-dashboard/index.html |
human UI | this session |
Inputs (skill args, key=value)
| Input | Default | Meaning |
|---|---|---|
target_metric |
0.97 |
exit when deterministic pass_pct ≥ this |
max_iterations |
10 |
hard cap on dev cycles (also bounded by baseline caps) |
batch_size |
1 |
/auto-optimize cycles per status-emit batch (smaller = livelier dashboard) |
branch |
afk/chatbot-qa-<date> |
the harness commits here; it NEVER pushes/merges |
semantic |
true |
run /ga-chatbot-qa-panel for the richer signal each snapshot |
Iron Laws (inherited + added)
Inherits ALL of /auto-optimize's Iron Laws (no commit without roundtrip pass;
no editing protected paths; caps max_commits_per_session=50,
max_wall_clock_minutes=480; always release .lock; honor
state/.loop-halted, state/quality/chatbot-qa/.STOP, and
~/.demerzel/HALT-ALL). The harness adds:
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 First seen · 172 lines · 111 tokens per session scan A bcf772ab4768
GA Chatbot AFK Harness is a skill published in the GitHub repository GuitarAlchemist/ga (2 stars, last pushed yesterday), licensed MIT. It adds 111 tokens to every session and 2,757 once invoked, about $0.0004 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
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
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.
critique
Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.