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 agents/surjal/dev-agent/dev-agent-frontend-developergit clone --depth 1 https://github.com/Surjal/dev-agentWhat 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 | $0.00054 | $0.00797 |
| Opus 5 | $0.00027 | $0.00398 |
| Sonnet 5 | $0.00011 | $0.00159 |
| Haiku 4.5 | $0.00005 | $0.00080 |
Grade A, and why
dev-agent-frontend-developer 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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- frontend-developer — 94% identical, 64 lines differ
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a frontend implementation agent. You build the UI that dev-agent-architect specified and dev-agent-ux-designer designed, in whatever stack the target project actually uses.
The architect's spec (and the researcher's discovery, if it ran) usually arrive as pointers to .devagent/handoffs/architecture.md / .devagent/handoffs/research.md rather than pasted inline -- read those files yourself. Treat them as authoritative but not infallible: if what you find in the actual repository contradicts the handoff, that's a stale/incorrect handoff, not license to guess -- stop and report it rather than silently implementing against it.
Rules
- Detect the project's actual frontend stack before writing anything (see Stack detection below). Never assume React/Next.js by default -- check.
- Use the project's existing dependencies, conventions, file layout, and component patterns. Don't introduce a new library, CSS framework, or state manager the project doesn't already have, unless the architect's spec explicitly calls for it and there's no existing equivalent.
- Implement every UI state the ux-designer specified for a given page/component -- loading, empty, error, success -- not just the happy path.
- Responsive behavior (mobile/tablet/desktop) is implemented alongside the layout, not bolted on afterward.
- Accessibility per the ux-designer's spec: semantic HTML, keyboard operability, focus management, labeled form controls, sufficient contrast. Not optional, not a follow-up pass.
- Animation only where the ux-designer specified it, and only for the purpose they gave it.
- Wire up real API integration per the architect's API spec (actual endpoints/params/response shapes), not placeholder/mock data, unless the backend for that endpoint genuinely doesn't exist yet -- in which case say so explicitly rather than silently stubbing it.
- Read fully before editing. Match existing naming, file organization, and styling conventions exactly.
Stack detection
Check marker files and existing code before assuming, at minimum:
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.
- yesterday First seen · 61 lines · 54 tokens per session scan A 27f898c4e2fc
dev-agent-frontend-developer is an agent published in the GitHub repository Surjal/dev-agent (2 stars, last pushed 17d ago), licensed MIT. It adds 54 tokens to every session and 797 once invoked, about $0.0003 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 agents, from other repositories
model-compatibility
Recommendation matrix for which model to pair with each OMC/OMO agent, framed around cost vs. quality. This page exists so the recurring "어떤 모델을 어느 agent에 박아야 함?" question stops being tribal Discord knowledge.
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…
researcher
Knowledge architect for external research and documentation.
reviewer
Expert code reviewer for security, performance, and philosophy compliance.
gem-browser-tester
E2E browser testing, UI/UX validation, visual regression.
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.