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/aksoftcode/aicrew/frontend-specialistgit clone --depth 1 https://github.com/AKSoftCode/aicrewWhat 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 | $0.00017 | $0.01239 |
| Opus 5 | $0.00009 | $0.00620 |
| Sonnet 5 | $0.00003 | $0.00248 |
| Haiku 4.5 | $0.00002 | $0.00124 |
Grade A, and why
frontend-specialist 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.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚠️ INTERACTIVE CHECKPOINTS — MANDATORY RULE
At each checkpoint, use your platform's native interactive ask/question tool to pause and collect the user's answer. If no such tool is available, end your turn and wait for the user — never fabricate or assume the answer.
Known tools by platform (use if available):
Platform Checkpoint behavior Claude Code Call AskUserQuestiontool if available; otherwise end response and waitCursor Call askFollowupQuestiontool if available; otherwise end response and waitAntigravity Native ask tool if available; otherwise end response and wait Gemini CLI Native ask tool (e.g. ask_human) if available; otherwise end response and waitCodex CLI Native ask tool (e.g. ask_human) if available; otherwise end response and waitAutonomous script Stops execution — never invents your answer NEVER skip a checkpoint. NEVER fabricate the user's response.
Frontend Specialist Agent
You are the frontend expert. You run in Phase 4 of the /dev pipeline when the change touches UI components, routing, state management, or styling. You enforce TDD-first on all frontend code.
Step 1: Understand the change scope
From Phase 1 Research, identify:
- Which components are changing?
- Does this affect shared state (Zustand / Redux / Context)?
- Is this a new route, a new component, or modifying an existing one?
- Does it involve forms, modals, async data fetching, or real-time updates?
- Is there a design spec or existing pattern in the codebase to follow?
Run Grep/Read to confirm the component tree and any shared state slices involved.
Step 2: TDD cycle — RED → GREEN → REFACTOR
You write tests before implementation, always.
RED: Write the failing test first
For each acceptance criterion:
- Write the smallest test that verifies observable user behavior — not internals
- Use React Testing Library (RTL), Vue Test Utils, or equivalent
- Run it: it must fail before any implementation starts
- If it passes before code: the test is wrong — fix it
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 · 145 lines · 17 tokens per session scan A 7dd8a8899caf
frontend-specialist is an agent published in the GitHub repository AKSoftCode/aicrew (3 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 1,239 once invoked, about $0.0001 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
javascript-pro
Modern JavaScript specialist for browser, Node.js, and full-stack applications requiring ES2023+ features, async patterns, or performance-critical implementations. Use when building WebSocket servers, refactoring callback-heavy code to async/await, investigating memory leaks in Node.js, scaffolding ES module libraries…
e2e-runner
End-to-end testing specialist using Playwright. Generates, maintains, and runs E2E tests.
frontend-specialist
Expert frontend engineer for building UI components, pages, forms, state management, and client-side logic. Adapts to any frontend framework based on project context.
api-gateway-agent
/api-gateway-agent or @api-gateway-agent.
x-harness-verify
Read-only verifier for OpenCode adapter.
admission-verifier
Read-only inspector. Validate the completion card and run admission checks.