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 acceptance-criteria-gwtgit 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/acceptance-criteria-gwt)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/acceptance-criteria-gwt"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/acceptance-criteria-gwt/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/acceptance-criteria-gwt"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/acceptance-criteria-gwt.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 | $0.01512 |
| Opus 5.5 | $0.00014 | $0.00605 |
| Sonnet 5.5 | $0.00007 | $0.00302 |
| Haiku 4.5 | $0.00003 | $0.00151 |
Grade A, and why
acceptance-criteria-gwt 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Acceptance Criteria (Given/When/Then)
Overview
Acceptance criteria are the contract QA tests the product against and the PM verifies at UAT. If a criterion isn't executable, it can't be verified — and unverifiable criteria are where defects hide.
Core principle: Every criterion is an observable behavior QA can execute with a command or a click path. No aspirational adjectives.
The shape
Given [precondition], When [action], Then [measurable result].
Where they go
Criteria live in the board task's own acceptance_criteria field — an array of strings, one criterion per item, passed to create_board_task (or update_board_task to replace the whole list). Each item becomes a checkbox the implementer ticks with set_criterion_completed, and that QA (in ready_for_qa/in_qa) and you (in pm_uat) then rule on independently with review_criterion. The tick is the implementer's claim — QA and PM never call set_criterion_completed; your verdict is review_criterion.
Never write them into description. A criteria block pasted as markdown leaves the task's checklist empty: nothing to tick, nothing the move guard can check, and the prose copy goes stale the moment the real criteria are edited.
Testability gate
For each criterion, before you save it, write down:
- who executes it — QA in in_qa, and the PM in pm_uat with browser or mobile tools (or
http_requestagainst the task's own preview when the surface is an API, not a screen); - the action — a click path, a URL, or a request;
- the exact observable — text, a count, an element state, or a file.
If the behaviour is user-facing, the Then must be visible in the UI — not a status code standing in for what the user sees. If nobody outside the code can observe it, it belongs in technical_description, not in a criterion.
Declarative When, concrete Then
Write the When as what happens, not the click-by-click path — the cucumber test: "Will this wording need to change if the implementation changes?" If yes, it's too imperative. One behaviour per criterion. Put exact copy strings in quotes in the Then; "an error appears" is not testable, "'Title must be at most 200 characters' appears under the field" is.
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 · 112 lines · 34 tokens per session scan A 783341f7af4f
acceptance-criteria-gwt is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 34 tokens to every session and 1,512 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 2026-10-05.
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.