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 pm-uat-reviewgit 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/pm-uat-review)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/pm-uat-review"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/pm-uat-review/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/pm-uat-review"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/pm-uat-review.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 | $0.00056 | $0.01753 |
| Opus 5.5 | $0.00022 | $0.00701 |
| Sonnet 5.5 | $0.00011 | $0.00351 |
| Haiku 4.5 | $0.00006 | $0.00175 |
Grade A, and why
pm-uat-review 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PM UAT Review
Overview
pm_uat is the PM's own gate, not a rubber stamp on QA's work. You have no code-reading tools here — codebase_search, grep_code, get_repo_tree, read_file and the rest are gone in this column — so your verdict can only come from evidence you produced yourself this run: a browser walk-through, a device walk-through, or a direct HTTP request. There is no backend exception: a criterion with no screen still gets your own executed evidence, never a pass on QA's word alone.
1. Inputs
- The task's ORIGINAL description and every acceptance criterion.
- The human's requirement comments on the task (injected as "The human's requirements written on this task"). Where they disagree with the original description or a criterion, the comment wins — and what it asks for needs evidence like any criterion.
- QA's evidence: the
review_criterionnote on each criterion, andlist_test_casesforpassedcases matchingcriterion_id. Both are a cross-check, never a substitute — you still walk every criterion yourself, covered or not.
2. Get a URL — never production
First one that applies: get_task_preview — a preview that is ready AND built_from_pr_head (its open_url); else get_deploy_target with env="stage", if this repository has a stage environment recorded; else start_task_preview and use its url once one appears (call it again if the URL isn't there yet — it will not restart a preview already starting).
3. Walk each criterion
UI-observable criteria: browser_navigate → browser_wait_for → browser_fill/browser_click through the flow, browser_screenshot as evidence. Check at phone (browser_set_viewport {device:"mobile", width:360}) and desktop at minimum for anything visual.
API-only criteria (no screen to walk, usually task_type: "technical" or a backend criterion on a task/bug): boot the task branch with start_task_preview, then use http_request against that preview's http://127.0.0.1:<port> URL (the tool refuses anything that is not this machine, so a stage or production URL is never an option for it; a read-only stage check is fetch_url) to exercise exactly what the criterion asks: happy path, invalid input, unauthorized/forbidden, whatever the criterion names. This is not optional and not QA's job to cover for you — every API criterion gets your own request in this run.
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 · 88 lines · 56 tokens per session scan A e0e2679e10cf
pm-uat-review is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 56 tokens to every session and 1,753 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
jetson-video-pipeline
Use when planning, executing, and independently validating Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decode, AV1, or concise acceptance workflows.
webapp-testing
Verify a local web app in a real browser with page, element, click, form, console and screenshot evidence. Use after a build or UI change; do not implement features or publish deployments with this skill.
C31-review
Reviews code changes using dynamically selected reviewer personas, then runs a verify-work pass: UAT walkthrough, verifier validation, and decision coverage logging. Writes memory/.planning/phases/XX-VERIFICATION.md.
textual-ui-developer
Develop and debug the MassGen Textual TUI with deterministic replay, snapshot regression tests, and targeted runtime checks.
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-task-bridge
Create, comment on, update, and list Paperclip tasks from Hermes using scoped Paperclip API credentials.