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 skills/renfei-design/fify-plugin/information-uinpx skills add renfei-design/fify-plugin --skill information-uigit clone --depth 1 https://github.com/renfei-design/fify-pluginWrote 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/renfei-design/fify-plugin/information-ui)<a href="https://agentmods.dev/skills/renfei-design/fify-plugin/information-ui"><img src="https://agentmods.dev/badge/skills/renfei-design/fify-plugin/information-ui.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 | $0.00082 | $0.00740 |
| Opus 5 | $0.00041 | $0.00370 |
| Sonnet 5 | $0.00016 | $0.00148 |
| Haiku 4.5 | $0.00008 | $0.00074 |
Grade A, and why
information-ui 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 3d 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.
What it actually says
Fify information UI
- Complete all factual reasoning, retrieval, and source checking before calling Fify. Fify is a presentation compiler, not a source of facts.
- Fast path: when the user already supplied the facts or source material needed for the requested view, treat that material as the grounding. Do not browse, enrich, or re-research it unless accuracy or freshness requires verification.
- Prepare the envelope in one pass and call the tool immediately after grounding. Do not inspect files, run shell commands, probe the renderer, or narrate internal composition work.
- Keep an authoritative plain-language answer. Pass it unchanged as
groundedAnswer; it is the fallback if UI is unsupported, unavailable, expired, or over quota. - Call only
render_information_ui. Never call or mentionread_information_ui_run; it is reserved for the mounted app.- When the user explicitly tags
@Fify, confirm thatrender_information_uiis available before doing extended retrieval or composition. - If the native tool is unavailable, fail fast with one short sentence. Do not create or edit files, run shell commands, inspect plugin internals, import the MCP SDK, or call Fify over HTTP as a workaround. Those paths cannot mount the native information UI.
- When the user explicitly tags
- Use
InformationEnvelopeV1version1.0:- Copy the user request into
originalRequestand use their locale when known. - Supply one to eight semantic sections and at most twelve items per section.
- Give every source, section, and item a stable unique semantic ID.
- Attach only source IDs that exist in
sources; use public HTTPS source URLs. - Optionally include up to four grounded
mediarecords when seeing the real subject materially improves the answer. Use only an exact openly licensed image URL already established during research fromupload.wikimedia.orgorapi.openverse.org, accurate alt text and caption, and an existingsourceId. Never invent, search for, or rewrite media during Fify composition; omit media if any provenance is uncertain. - Include no more than two short natural-language refinements.
- Keep the whole envelope under 24,000 characters.
- Copy the user request into
- Invoke automatically only when structure or non-consequential interaction adds material value: comparisons, plans, timelines, trackers, structured explanations, decision tools, and editable summaries are strong cases.
- Always invoke when the user tags
@Fifyor says “show this as an interactive view,” unless the requested UI would be unsafe or consequential. - After the widget mounts, do not repeat the complete answer. Give at most one short sentence orienting the user; the tool already returns the authoritative text fallback.
- For follow-up refinements, call the same public tool with a newly grounded envelope. Preserve compatible semantic IDs and pass prior checked, selected, or input state in
continuationStatewithout exposing it to the user. - Keep v1 non-consequential. Selection, filtering, checklists, disclosure, local inputs, and conversational refinements are allowed. Purchasing, publishing, account changes, and third-party mutations are not.
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.
- 3d ago First seen · 28 lines · 82 tokens per session scan A 964f94f974b1
information-ui is a skill published in the GitHub repository renfei-design/fify-plugin (1 stars, last pushed 10d ago), licensed Apache-2.0. It adds 82 tokens to every session and 740 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 2026-08-31.
Other skills, from other repositories
flint-theme-author
Use when: creating, translating, refining, reviewing, or validating a custom Flint ThemeSpec from brand guidelines, websites, slide decks, publication references, design tokens, or an existing visual identity. Produce a reusable ThemeSpec JSON object for Flint Theme Lab without inventing fields or changing chart…
dashboard-design
Use this skill first when the user wants to design or plan a dashboard, especially Vizro dashboards. Enforces a 3-step workflow (requirements, layout, visualization) before implementation. Activate when the user asks to create, design, or plan a dashboard. For implementation, use the dashboard-build skill after…
designing-vizro-layouts
Use this skill when designing or building Vizro dashboard layouts — grid configuration, component sizing, filter/parameter placement, selector types, or container patterns. Activate when the user is creating wireframes, defining page structure, placing controls, or sizing charts.
codex-slides
Create, research, revise, restyle, present, inspect, and export Codex Slides slide decks from Codex, including scenario workflows, project Design Files, and always-on brand design systems. Use when the user asks for a presentation, PPT/PPTX, slide deck, research brief converted into slides, an existing deck edit, a…
superloopy-clone
Use when the user asks for Superloopy clone or asks to clone, rebuild, reverse-engineer, replicate, or copy a website or page into a Superloopy-governed implementation. Triggers on "loopy clone", target URLs plus requests such as "clone this site", "rebuild this page", "make a copy of this website", "pixel-perfect…
codex-slides-deck
Compatibility entry point for scenario-led creation, Design Files, brand systems, inspecting, revising, restyling, and exporting Codex Slides slide decks. Use when a user asks Codex to make a presentation, use project files, edit an existing deck, manage slide structure, apply brand or template rules, or export…