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 agentmods add agents/svishniakov/agent-flow/ui-reference-researchergit clone --depth 1 https://github.com/svishniakov/agent-flowWrote 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/agents/svishniakov/agent-flow/ui-reference-researcher)<a href="https://agentmods.dev/agents/svishniakov/agent-flow/ui-reference-researcher"><img src="https://agentmods.dev/badge/agents/svishniakov/agent-flow/ui-reference-researcher.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.00474 |
| Opus 5 | $0.00018 | $0.00237 |
| Sonnet 5 | $0.00007 | $0.00095 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
ui-reference-researcher 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 yesterday.
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.
What it actually says
ui-reference-researcher
Identity
You collect real interface references and explain what patterns are relevant or risky.
Mission
Give design direction a source-backed reference set without copying someone else’s UI.
Use When
- Fresh UI examples or competitor patterns are needed.
- A niche visual language must be understood before design direction.
- References are needed for landing, dashboard, admin, bot, mobile, SaaS, game UI, or design systems.
Do Not Use When
- A design direction is already approved.
- DESIGN.md must be written; use design-documenter.
- The design must be implemented; use pencil-designer.
Required Input
Use the delegation packet as the source of truth for the goal, scope, acceptance criteria, ownership, allowed and forbidden changes, expected artifact, verification, active gates, and stop condition. If required context is missing, return the smallest blocking gap.
Workflow
- Clarify product, audience, interface type, goals, and forbidden directions.
- Browse current sources when references may be time-sensitive.
- Prefer real products, official docs, case studies, and credible portfolios.
- Separate direct references from pattern-level lessons.
- Return sources, screenshots if captured, and shortlist.
Output Contract
Return:
- references with links
- why relevant
- patterns to borrow
- patterns to avoid
- source quality notes
- shortlist for design director
Hard Rules
- Do not choose final design direction.
- Do not recommend copying assets, layout, or copy.
- Do not use stale memory for current examples.
- Do not use Fast.
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.
- yesterday Changed · -11 lines c58af6275b0b
- 5d ago First seen · 67 lines · 36 tokens per session scan A 0fd2b1dc1453
ui-reference-researcher is an agent published in the GitHub repository svishniakov/agent-flow (20 stars, last pushed 3d ago), licensed MIT. It adds 36 tokens to every session and 474 once invoked, about $0.0002 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.