Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jakyeamos/tmcpnpx agentmods add skills/jakyeamos/tmcp/tmcp-ui-rubricWrote 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/jakyeamos/tmcp/tmcp-ui-rubric)<a href="https://agentmods.dev/skills/jakyeamos/tmcp/tmcp-ui-rubric"><img src="https://agentmods.dev/badge/skills/jakyeamos/tmcp/tmcp-ui-rubric/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/jakyeamos/tmcp/tmcp-ui-rubric"><img src="https://agentmods.dev/badge/skills/jakyeamos/tmcp/tmcp-ui-rubric.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 | $0.00035 | $0.00489 |
| Opus 5 | $0.00017 | $0.00244 |
| Sonnet 5 | $0.00007 | $0.00098 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
tmcp-ui-rubric 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 10d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TMCP UI Rubric
Status: experimental. This workflow remains shipped and callable, but its public contract may change.
Use this skill when the user asks for a UI audit, expert UI rubric, visual quality review, product polish review, responsive UI assessment, design-system fit review, or a remediation plan for interface quality.
Prefer this over a generic browser-only review when the user asks to score, judge, audit, prioritize, or plan UI remediation. Do not use it for tiny copy/style edits or immediate implementation unless the user explicitly asks for edits.
Workflow
- Gather concrete UI evidence when available: screenshots, browser inspection, relevant components, design rules, accessibility constraints, product context, and known target users.
- Invoke TMCP through MCP tools when exposed:
tmcp_explainfor the task-specific packet.expert_rubric_review_planfor the scored rubric, audit, and remediation plan.
- If MCP tools are not exposed, or
tool_searchreturns no TMCP tools even though this skill is installed, use the CLI from the TMCP plugin root. First verify the local launcher if needed:
node scripts/tmcp_launcher.mjs doctor --client codex
node scripts/tmcp_launcher.mjs list-tools
Then run the UI rubric workflow:
node scripts/tmcp_launcher.mjs expert-ui-rubric --project-path "<project-path>" --evidence-json '<json>' --write-artifacts
- If the CLI works but Codex tool discovery does not expose TMCP tools, state that as a Codex MCP discovery gap and continue with CLI-generated TMCP artifacts rather than downgrading to a generic UI review.
- If rendered UI evidence is unavailable, say that explicitly and base findings on source evidence only.
- Stop at the audit/remediation plan unless the user explicitly approves implementation.
Output Contract
Produce or cite:
- TMCP expertise packet or
tmcp_explainoutput. - Packet
substance_check. - Scored UI rubric.
- Evidence-backed findings or explicit evidence gaps.
- Ordered remediation plan with verification expectations.
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.
- 10d ago First seen · 47 lines · 35 tokens per session scan A 6b7e6f381b1d
tmcp-ui-rubric is a skill published in the GitHub repository jakyeamos/tmcp (0 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 489 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 2026-08-31.
Other skills, from other repositories
developing-with-streamlit
Use for ALL Streamlit tasks: creating, editing, debugging, beautifying, styling, theming, optimizing, or deploying Streamlit apps. Also custom components, st.components.v2, HTML/JS/CSS work. Discovers and loads version-matched reference docs from the user's installed Streamlit (>=1.57). Triggers: streamlit, st.…
huggingface-gradio
Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.
wiring-vizro-actions
Use this skill when adding cross-filter, cross-highlight, drill-through, or data export interactions to a Vizro dashboard — both for choosing the right interaction pattern during design and for implementing actions in code. Activate when the user wants clicks on a chart or table to filter or highlight other charts…
stripe-apps
Use when building, modifying, or reviewing a Stripe App — or when the user describes something that implies one (e.g. "add a panel to the customer page", "customize my Stripe Dashboard", "react to Stripe events from my app", "connect my service to Stripe without sharing API keys"). Covers the full app development…
frontend-feature
Build a new page, view, or data-driven feature in the Next.js frontend. Use when adding a route under the dashboard/marketing area, wiring UI to a backend endpoint, adding client state, or creating a localized page. Covers App Router, data fetching, Zustand stores, and i18n.
pwa-development
Progressive Web Apps - service workers, caching strategies, offline, Workbox.