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 instructions/tn0123/one-shot-ui/agents-mdgit clone --depth 1 https://github.com/TN0123/one-shot-uiWrote 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/instructions/tn0123/one-shot-ui/agents-md)<a href="https://agentmods.dev/instructions/tn0123/one-shot-ui/agents-md"><img src="https://agentmods.dev/badge/instructions/tn0123/one-shot-ui/agents-md.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 5.1 | $0.02425 | $0.02425 |
| Opus 5 | $0.01213 | $0.01213 |
| Sonnet 5 | $0.00485 | $0.00485 |
| Haiku 4.5 | $0.00243 | $0.00243 |
Grade A, and why
one-shot-ui AGENTS.md 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 5d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
one-shot-ui
Deterministic UI extraction and comparison toolkit. Use this tool to see what is wrong with a UI implementation compared to a reference screenshot.
Installation
npm install -g one-shot-ui
npx playwright install chromium # only needed for capture/run commands
Core Workflow
-
Extract — Analyze a reference screenshot into structured layout data: one-shot-ui extract reference.png --json For Retina/Mac screenshots, add
--dpr 2so font sizes and bounds are reported in CSS pixels (a 2x capture otherwise doubles every measurement). When omitted, scale is auto-detected; check the report'sscale/unitsand re-run with--dpr 2if it hints the image is Retina. -
Build — Use the extracted data (colors, spacing, typography, tokens) to build your implementation. The agent should write the UI code directly. Build to the
rulersblock (band heights, column edges + widths, gutter widths — all CSS px) to get sizing/spacing right the first time. Don't hand-draw icons/glyphs as SVG or CSS — use an icon library (the codebase's existing set, elselucide;@primer/octiconsfor GitHub-style UIs). Hand-drawn glyphs are the most common residual diff. -
Capture — Screenshot your implementation at the reference's exact scale: one-shot-ui capture --file ./index.html --match-reference reference.png --output impl.png
--match-referencematches viewport AND device scale (a 2x Retina reference is captured at CSS dims @ 2x), so pixels line up without resize/crop. Add--reference-dpr 2if the reference is Retina and the capture reports low DPR confidence. -
Compare — Diff reference vs implementation: one-shot-ui compare reference.png impl.png --json --heatmap heatmap.png Use
summary.verdict(converged/not-converged+ reasons) as your stop signal — not the pixelmismatchRatio, which is background-dominated and reads as "almost done" even when most elements are missing. Keep iterating until the verdict isconverged. The report'sspacing[]array gives deterministic, directly-CSS-able sizing/spacing deltas (BAND_HEIGHT_DELTA,EDGE_X_DELTA,GUTTER_DELTA) with concrete fixes — apply these first; they're the highest-trust path to closing the last-mile spacing gap.compare … --spacingprints just this list.
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.
- 5d ago First seen · 155 lines · 2,425 tokens per session scan A 9bdeb8dc493c
one-shot-ui AGENTS.md is an instructions file published in the GitHub repository TN0123/one-shot-ui (4 stars, last pushed 1mo ago), licensed MIT. It adds 2,425 tokens to every session, about $0.0121 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 instructions, from other repositories
roamcode AGENTS.md
AGENTS.md instructions for burakgon/roamcode, covering repository instructions for coding agents, public-repository safety, stable release and ota contract, releasing a stable version and ota changes.
amp-acp AGENTS.md
Instructions for tao12345666333/amp-acp, covering agents.md, commands, architecture and code style.
dev-workspace AGENTS.md
Instructions for iwe-org/dev-workspace, covering agent operating manual, start of every session, the operating loop, conventions and iwe basics.
ob-1 AGENTS.md
Instructions for Overbrilliant/ob-1, covering agents.md, project index, stack, commands and key files.
kumo-coding-agent AGENTS.md
Instructions for kumo-ai/kumo-coding-agent: All instructions, routing tables, and rules are in CLAUDE.md. Read that file as the entry point for this agent.
tidyfactor-design AGENTS.md
Instructions for alwkala/tidyfactor-design, covering ⚡ skill & 24 modular slash commands (7 lifecycle stages) and critical architecture (non-negotiable).