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 makifbaysal/tasktrooper --skill qa-verify-before-verdictgit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/makifbaysal/tasktrooper/qa-verify-before-verdict)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/qa-verify-before-verdict"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/qa-verify-before-verdict/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/makifbaysal/tasktrooper/qa-verify-before-verdict"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/qa-verify-before-verdict.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 | $0.00040 | $0.01094 |
| Opus 5.5 | $0.00016 | $0.00438 |
| Sonnet 5.5 | $0.00008 | $0.00219 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade A, and why
qa-verify-before-verdict 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 8d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify Before Verdict
No verdict without fresh executed evidence in this run.
- Every case on the task gets a result you recorded yourself:
passedorfailedwith the exact command and its observed output (actual), UI cases additionally with a one-line evidence string (width/device, URL, viewport report, what it showed — never a screenshot path, there isn't one; frontend-manual-testing / mobile-manual-testing). The result belongs on the case (set_test_case_result), not in a comment — that is where the next reader looks, and it survives the run. - A case you could not execute is
skippedwith what blocked it (no device, no stage deploy, missing credential), neverpassed. A case stillplannedwhen you try to hand the task on refuses the move. - A pass verdict rests on ONE thing this iteration: every case executed manually by you, with its evidence. Writing automated tests is out of scope for now — do not add suites and do not hold a verdict waiting for one. The repository's existing pipeline is still read (
get_pipeline_status): red is a finding, green is not a substitute for your own run. - A criterion is approved (
approved=true) only when you executed and observed it pass this run AND at least onepassedtest case carries itscriterion_id— an approval with no linked passed case is what pm_uncovered_criterion rejects at PM UAT. A criterion you could not execute is never approved: say which one, what blocked it and what would unblock it. - Both verdicts are moves out of
in_qa— the column you took the task into before testing. All cases green → move it to pm_uat with the evidence on the cases and the criteria approved — except a task whosetask_typefield istechnical: move it straight to human_uat instead, same evidence, same "no comment" rule. A backend-only, API-only or infrataskorbugstill goes to pm_uat; the field decides, never what the change touches. Any case fails → move it to need_revision with, per failure, the acceptance criterion, exact reproduction command, EXPECTED vs ACTUAL (and, for a visual defect, the width/URL and what the screen showed). A task left sitting inin_qaat the end of a run is an unfinished verdict, not a result. - What actually fails a task vs. what is a note on a passing criterion: see bug-report-writing's rubric. Taste and polish beyond the team's UI floor are notes, never failures.
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.
- 8d ago First seen · 42 lines · 40 tokens per session scan A acb4fe059d32
qa-verify-before-verdict is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 40 tokens to every session and 1,094 once invoked, about $0.0002 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 2026-10-05.
Other skills, from other repositories
qa-acceptance
Produce QA acceptance criteria and a manual validation plan for a feature change — golden path, edge cases, error states, performance limits, and explicit pass/fail evidence.
paperclip
Use for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and following company governance. Includes control plane API operations for assignments, comments, approvals, and routines.
paperclip-board
Manage a Paperclip company as a board member via chat. Use when the user wants onboarding, company or agent management, approvals, task monitoring, cost oversight, or work product review in the Paperclip control plane.
paperclip-distill
Use when an operation issue is a Paperclip cursor-window, distill, or backfill. Turn source-bundled Paperclip activity into wiki-insightful project standups, durable project pages, decisions, and history without asset dereferencing.
summarize-status
Write a short, colloquial summary for a Paperclip summary slot: open with the 1–3 specific, concrete actions the reader needs to take right now to unblock the work, then a brief plain-language status, streaming progress as it works.
paperclip-task-bridge
Create, comment on, update, and list Paperclip tasks from Hermes using scoped Paperclip API credentials.