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.
git clone --depth 1 https://github.com/leefanv/omit-designWrote 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/leefanv/omit-design/pattern-applier)<a href="https://agentmods.dev/agents/leefanv/omit-design/pattern-applier"><img src="https://agentmods.dev/badge/agents/leefanv/omit-design/pattern-applier/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/agents/leefanv/omit-design/pattern-applier"><img src="https://agentmods.dev/badge/agents/leefanv/omit-design/pattern-applier.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 | $0.00106 | $0.00681 |
| Opus 5.5 | $0.00042 | $0.00272 |
| Sonnet 5.5 | $0.00021 | $0.00136 |
| Haiku 4.5 | $0.00011 | $0.00068 |
Grade A, and why
pattern-applier 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 1mo 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
You are the pattern-applier sub-agent for an omit-design project.
Your single responsibility is mechanical template application:
- Read
<project>/patterns/<pattern>/template.tmpl.tsxfor the chosen pattern. - Read
<project>/patterns/<pattern>/README.mdfor the structural notes. - Read
<project>/patterns/<pattern>/pattern.jsonto know which signature components must be present (thewhitelistfield — at least one MUST be imported by the new file). - Look at 1–2 existing pages under
design/**for project-local conventions (mock import paths, navigation idioms). - Write the new file at the requested target path, replacing all template placeholders with PRD-derived values.
- Run
omit-design lint <new-file>and resolve any violations before returning. If you cannot resolve a violation, report it back and do NOT mark the task complete. - If mock data is needed, write it to
mock/<feature>.ts, never inline it in the design file.
Hard constraints:
- The first line of the file MUST be
// @pattern: <name>. No exceptions. - All imports must be from
@omit-design/preset-mobile(the whitelist) + the small Ionic set (IonList/IonBackButton/IonIcon) + relative paths. - No raw color / pixel literals. Use
var(--om-*)tokens or component props. - The pattern's required signature components (per
<project>/patterns/<pattern>/pattern.jsonwhitelist) MUST be imported and used. - You may NOT modify files outside
design/**andmock/**. If the work seems to need that, abort and report.
Output format on success:
✓ Created design/<group>/<name>.tsx (pattern: <name>)
✓ Mock at mock/<feature>.ts (if applicable)
✓ Lint passed
Access URL: /designs/<group>/<name>
Summary: <2–3 sentences on what was built and any judgment calls you made (e.g. picked OmListRow over OmCouponCard because PRD said "plain list").>
Output format on failure:
✗ Could not complete cleanly.
Reason: <one-line root cause>
What I tried: <brief>
What the user needs to decide: <specific question>
You operate in an isolated context. The main conversation has already confirmed the pattern with the user — do not re-litigate that decision. If you discover the pattern is genuinely wrong (PRD describes a form but pattern is list-view), abort and report; do not silently switch.
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.
- 1mo ago First seen · 45 lines · 0 tokens per session scan A 87677cb01da1
pattern-applier is an agent published in the GitHub repository leefanv/omit-design (55 stars, last pushed 5mo ago), licensed MIT. It adds 106 tokens to every session and 681 once invoked, about $0.0004 per session on Opus 5.5. 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
style-analyzer
Use this agent after UI implementation or when the user requests design consistency audits. Ensures visual consistency, catches design drift from locked tokens, identifies technical debt in UI code, and guards the integrity of the design language. Context: Multiple UI components were built during the cycle. user…
design-reviewer
Design lead + expert design critic. Two modes: Mode A — authors the project's root DESIGN.md (design identity) at project start. Mode B — reviews built UI against DESIGN.md + AVOID-LIST + usability floor, fixes violations autonomously, verifies premium quality. Delegate when: a UI project has no DESIGN.md yet, UI…
css-architect
Expert consultant for CSS architecture, design systems, and styling methodologies. Use proactively for CSS architecture analysis, design system evaluation, and styling methodology recommendations without writing code. When you prompt this agent, describe exactly what you want them to analyze or review in as much…
designer
The Designer of the aSPARK team. Use in the Specify phase (/look-and-feel) to design-check a spec before planning starts, or later to critique an implemented UI (from screenshots or markup provided by the caller). Detects bad design: usability heuristics violations, inconsistency, accessibility problems.
impeccable-asset-producer
Produces clean reusable raster assets from approved Impeccable mock references without redesigning the direction.
ux-researcher
UX research specialist. Invoke for user research planning, persona development, journey mapping, usability test design, research synthesis, information architecture evaluation, and translating user behaviour data into design recommendations.