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 design-conformancegit 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/design-conformance)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/design-conformance"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/design-conformance/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/design-conformance"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/design-conformance.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 | $0.00060 | $0.01541 |
| Opus 5.5 | $0.00024 | $0.00616 |
| Sonnet 5.5 | $0.00012 | $0.00308 |
| Haiku 4.5 | $0.00006 | $0.00154 |
Grade A, and why
design-conformance 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 4d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Conformance
Overview
A task built from an approved design is tested against that design too. A human approved it before any code was written, and its hand-off spec is the contract the developer built to — an oracle like the acceptance criteria and the analysis spec. You read the design documents, never the code (black-box-testing), and compare what the running product shows with what they say.
Core principle: The approved design is the expected result. Same widths, same states, side by side — every finding cites the hand-off line or the mockup frame it contradicts, and the screenshot that shows it.
Inputs
- The hand-off spec —
handoff: <screen>, first under "## The approved design this task builds": the components, the tokens, every state, the breakpoints, the exact copy. Its header names the chosen mockup,design: <screen> · <letter>; the other variant documents were not chosen — never test against them. - The chosen mockup — its text rendition follows the hand-off in your context. To see a frame's look, render it under
$QA, never the workspace:list_task_documents <design key>withraw: true(follownext_offsetto the end), write it with a quoted heredoc (mkdir -p "$QA/design"; cat > "$QA/design/<slug>.html" <<'TT_HTML'…TT_HTML), serve it on loopback (nohup python3 -u -m http.server 0 --bind 127.0.0.1 --directory "$QA/design" > "$QA/design.log" 2>&1 & echo $! > "$QA/design.pid", the port is in the log),browser_navigatethere and screenshot the frame you compare. Stop it by its PID (stop-what-you-started). - The task's scope — where the task description and the design disagree, the description is the narrower scope and wins for this task; a part of the design outside it is not a finding.
Cases
Add them to the matrix before you boot anything (scenario-plan-first): category visual, title prefix design: (design: invoices empty 375 -> matches #a-375-empty), linked to the criterion that names the state or the copy when there is one — the designer's hand-off criteria usually do. One case per state the hand-off lists, per width:
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.
- 4d ago First seen · 62 lines · 60 tokens per session scan A 8ff152bb2fb0
design-conformance is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 60 tokens to every session and 1,541 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 2026-10-09.
Other skills, from other repositories
wireframe
Produce low-fidelity black-and-white UI wireframes as SVGs or viewer pages. Use when asked to wireframe, sketch a screen, draft a layout, make a low-fi mockup, or publish wireframes.
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.
design-critique
Give a structured product design critique — user job clarity, hierarchy, affordance, error states, accessibility, and consistency — focused on what to change, in what order, and why.
paperclip-capsules
Generate, implement, or review Paperclip capsule visuals. Use for capsule art, agent capsules, heartbeat status capsules, identicons, capsule banks, or brand-usage validation.
presentation-template-designer
Plan reusable presentation templates from a creative brief, optional brand assets, or an existing deck. Use when Codex needs to define a slide inventory, choose an editable presentation toolchain, author or validate a template manifest, adapt a visual system for PowerPoint or Google Slides, or prepare a reviewed…
design-before-build-gate
Enforces a design/spec approval gate before production implementation. Use when UI, UX, product flows, architecture, API shape, prototypes, visual direction, or user-facing behaviour need signoff before builders write production code.