pattern-applier

A helper agent that creates a new omit-design page from a selected pattern, target path, and product requirements document (PRD), which describes what the page should do.

In plain words
What is it for?
Use it to apply an existing pattern to a new design page, add mock data when needed, and run the page's lint check.
Why use it?
It removes repetitive template copying and checks the generated page against the project's design rules.

Agent

Install

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.

agentmods
npx agentmods add agents/leefanv/omit-design/pattern-applier
Clone the repo
git clone --depth 1 https://github.com/leefanv/omit-design
Per session 106 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 681 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00106 $0.00681
Opus 5 $0.00053 $0.00341
Sonnet 5 $0.00021 $0.00136
Haiku 4.5 $0.00011 $0.00068

Measured 2d ago against content hash 87677cb01da1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

agents/pattern-applier.md · 45 lines

What it actually says

You are the pattern-applier sub-agent for an omit-design project.

Your single responsibility is mechanical template application:

  1. Read <project>/patterns/<pattern>/template.tmpl.tsx for the chosen pattern.
  2. Read <project>/patterns/<pattern>/README.md for the structural notes.
  3. Read <project>/patterns/<pattern>/pattern.json to know which signature components must be present (the whitelist field — at least one MUST be imported by the new file).
  4. Look at 1–2 existing pages under design/** for project-local conventions (mock import paths, navigation idioms).
  5. Write the new file at the requested target path, replacing all template placeholders with PRD-derived values.
  6. 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.
  7. 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.json whitelist) MUST be imported and used.
  • You may NOT modify files outside design/** and mock/**. 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.

Changes

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.

  1. 2d ago First seen · 45 lines · 0 tokens per session scan A 87677cb01da1

Subscribe to this mod's changes

pattern-applier is an agent published in the GitHub repository leefanv/omit-design (54 stars, last pushed 3mo ago), licensed MIT. It adds 106 tokens to every session and 681 once invoked, about $0.0005 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.

Related

Other agents, from other repositories

presentation-claude-gemini

PROACTIVELY use this agent whenever the user wants to update, modify, rearrange, or fix the CLAUDE-GEMINI presentation (presentation/2026-04-25-gdg-kolachi-cli-claude-code-gemini/index.html) — slides, structure, styling, journey bar levels, or day/level organization. Do NOT use this agent for the vibe-coding…

shanraisshan/claude-code-best-practice · 101 tokens

presentation-claude-code

PROACTIVELY use this agent whenever the user wants to update, modify, rearrange, or fix the CLAUDE-CODE-BEST-PRACTICE presentation (presentation/claude-code-best-practice/index.html) — slides, structure, styling, level transitions, or content reuse from other decks. This is the canonical reusable Claude Code…

shanraisshan/claude-code-best-practice · 125 tokens

presentation-vibe-coding

PROACTIVELY use this agent whenever the user wants to update, modify, or fix the VIBE-CODING presentation (presentation/vibe-coding-to-agentic-engineering/index.html) — slides, structure, styling, or level transitions. Do NOT use this agent for the claude-gemini presentation (use presentation-claude-gemini instead).

shanraisshan/claude-code-best-practice · 82 tokens

ux-designer

Produces a concise, accessible UX brief with flows, states, and annotations.

shanraisshan/claude-code-best-practice · 19 tokens

ui-builder

Expert UI builder that creates complete, production-ready user interfaces immediately. Delegate when: creating pages, components, layouts, forms, or any visual UI work. Self-sufficient: reads requirements, builds UI with animations, verifies quality, fixes issues - all autonomously. Premium mode: multi-page…

wasintoh/toh-framework · 68 tokens

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…

wasintoh/toh-framework · 85 tokens