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 sergekostenchuk/ui-ux-agent-skill-system --skill design-feedback-collectorgit clone --depth 1 https://github.com/sergekostenchuk/ui-ux-agent-skill-systemWrote 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/sergekostenchuk/ui-ux-agent-skill-system/design-feedback-collector)<a href="https://agentmods.dev/skills/sergekostenchuk/ui-ux-agent-skill-system/design-feedback-collector"><img src="https://agentmods.dev/badge/skills/sergekostenchuk/ui-ux-agent-skill-system/design-feedback-collector/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/sergekostenchuk/ui-ux-agent-skill-system/design-feedback-collector"><img src="https://agentmods.dev/badge/skills/sergekostenchuk/ui-ux-agent-skill-system/design-feedback-collector.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 | $0.00076 | $0.00626 |
| Opus 5 | $0.00038 | $0.00313 |
| Sonnet 5 | $0.00015 | $0.00125 |
| Haiku 4.5 | $0.00008 | $0.00063 |
Grade A, and why
design-feedback-collector 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 12d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Feedback Collector
This skill turns comments into a controlled feedback register. It is not a visual critic by itself; it structures feedback so the chair and specialist skills can act without losing context.
Operating Modes
collect: gather user comments, agent critiques, and review-board notes.triage: assign severity, owner, affected skill, affected subprocess, and decision status.resolve: convert feedback into accepted, partially accepted, rejected, or applied decisions.sync-dashboard: update review-board or task-plan-facing summaries.sync-progress: update progress-screen user gates and feedback artifacts after a user decision.handoff: send accepted feedback to the right specialist skill.
Required Workflow
- Read references/feedback-status-contract.md.
- Use assets/feedback-register.schema.json as the register shape.
- Separate feedback sources:
- user comment;
- colleague/agent critique;
- validation finding;
- council decision.
- Assign each item:
- target skill or subprocess;
- severity;
- status;
- owner;
- required action;
- evidence needed.
- Use color/status semantics:
- blue: no comment/open empty state;
- red: unresolved comment exists;
- orange: partially accepted or partially applied;
- green: accepted and applied.
- For progress-screen gates, preserve
gate_id, selected option, comment, target phase/subprocess, and source artifact. - Do not mark an item applied unless the changed artifact or decision record is referenced.
Safety Rules
- Remove secrets, tokens, private URLs,
.envvalues, recovery codes, and private screenshots from feedback before saving. - Do not collapse disagreement into a fake consensus; preserve rejected and partially accepted reasoning.
- For high-impact disagreements, route to
senior-ui-ux-orchestratorin council mode.
Handoff Shape
Feedback mode:
Target skill/subprocess:
Source:
Status:
Severity:
Decision:
Applied artifact:
Open risk:
Next owner:
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 72 lines · 76 tokens per session scan A c02e6b127bf7
design-feedback-collector is a skill published in the GitHub repository sergekostenchuk/ui-ux-agent-skill-system (23 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 76 tokens to every session and 626 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.