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-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/design-review)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/design-review"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/design-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/design-review"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/design-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 | $0.00055 | $0.01107 |
| Opus 5.5 | $0.00022 | $0.00443 |
| Sonnet 5.5 | $0.00011 | $0.00221 |
| Haiku 4.5 | $0.00006 | $0.00111 |
Grade A, and why
design-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 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Review
Overview
A design review answers one question: does the built screen match the design the human approved? It is a comparison against a contract, not a fresh critique — taste that is not in the approved design is not a finding. You report problems; the developers decide the fix.
Core principle: Same widths, same states, side by side — every finding cites what the approved design says and what the build shows.
Inputs
- The approved design: the design task this review points at (its key is in the description,
blocked_byorderived_from; its documents are in your context under "## The approved design this task builds" when this task is blocked by it) —list_task_documents <key>: thehandoff: <screen>spec, which names the chosendesign: <screen> · <letter>mockup, and that mockup (raw: truefor its source, to render it). The other variant documents were not chosen; never review against them. - The built screen: the URL the description names (a preview or staging address), or the app started locally the way
get_project_briefsays — detached, its log under/tmp/tt-<task key>/, on loopback. Installing dependencies to run it is not a change; editing a source file is. get_design_systemfor the repository — the tokens the build must use.
Procedure
- Render the approved mockup (screen-mockup-html's self-check) and open the built screen in the same browser session, one after the other.
- At each width —
browser_set_viewport{device: "desktop"}(1440),{device: "tablet"}(768),{device: "mobile", width: 375}—browser_screenshotthe built page (full_page: true, nowidth,attach_to_task: true,title: "<screen>-built-<width>", plus-<state>for a state:invoices-built-375-empty) and the matching mockup frame (no need to attach it — it is on the design task already). - Reach every state the build allows from the outside: an empty search, a filter with no results, an invalid form submit, the error a disconnected API produces if the brief names one. A state you cannot reach is listed as "not reviewed", never assumed to match.
- Compare in this order: layout and hierarchy → content and exact copy → components (the right one, the right variant) → tokens (colour, type, spacing, radius —
browser_read_domwithas_text: falseshows the classes an element carries) → states → responsive behaviour → visible accessibility (labels, focus ring, text alternatives, touch target size). - Triage every difference:
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 · 54 lines · 55 tokens per session scan A 71e401cd2c6a
design-review is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 55 tokens to every session and 1,107 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.
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.
architecture-design
Use this skill to design system architecture with documented trade-offs and decisions before any implementation begins. Activates when a feature, system, or component requires non-trivial structural decisions about how components interact, what data stores to use, or how to decompose a problem.