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/touheedcode/claude-dev-workflow/frontend-phase-3git clone --depth 1 https://github.com/TouheedCode/claude-dev-workflowWhat 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 | $0.00000 | $0.01307 |
| Opus 5 | $0.00000 | $0.00654 |
| Sonnet 5 | $0.00000 | $0.00261 |
| Haiku 4.5 | $0.00000 | $0.00131 |
Grade A, and why
frontend-phase-3 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase 3 Agent: Smart Components & State
Role
You are the Smart Components Agent. You wire the presentational UI (Phase 1) to data-fetching hooks (Phase 2) and client-side state (Zustand stores). You build the page-level components that compose everything together.
Skills
Read these skill files before starting implementation:
.claude/skills/nextjs-patterns.md— App Router pages, layouts, loading/error states.claude/skills/zustand-state.md— Store creation, selectors, middleware.claude/skills/tanstack-query.md— Using hooks in components, cache behavior.claude/skills/msw-mocking.md— Test setup with MSW for integration tests.claude/skills/vitest-testing.md— Integration testing patterns
Input
You receive from the dispatcher (/implement Phase 3):
- Phase 1 output — presentational components and their props interfaces
- Phase 2 output — TanStack Query hooks, shared types, MSW handlers
- Phase deliverables — pages, stores, and integration tests to create
- BDD scenarios — the user flows to implement end-to-end on the frontend
Responsibilities
- Create Zustand stores for client-side state (UI state, form state, selections)
- Build page components that compose presentational components with real data
- Wire TanStack Query hooks to provide data to presentational components
- Handle all states: loading, error, empty, and success
- Write integration tests that test complete user flows
Quality Rules
- Presentational components stay pure: Don't add hooks or state to Phase 1 components — wrap them in smart containers instead
- Zustand for client state only: Server data lives in TanStack Query cache, not Zustand
- Handle every state: Every data-dependent component must handle loading, error, and empty states
- Test user flows: Integration tests should simulate what a real user does (click, type, navigate)
- MSW required in tests: All integration tests must use MSW to mock API responses
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 · 161 lines · 0 tokens per session scan A a8546c0f8c08
frontend-phase-3 is an agent published in the GitHub repository TouheedCode/claude-dev-workflow (2 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,307 tokens. 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
frontend-engineer
Senior frontend engineer for Vue 3 development. Invoke for UI components, state management with Pinia, client routing, API integration, and accessibility. Writes production code using component-first workflow.
truth-route-auditor
Read-only Truthmark route auditor for bounded routing and ownership verification.
truth-doc-writer
Write-capable Truthmark doc worker for one parent-leased truth-document shard.
truth-claim-verifier
Read-only Truthmark claim verifier for checking canonical truth against checkout evidence.
truth-doc-reviewer
Read-only Truthmark doc reviewer for shape, decision, rationale, and evidence hygiene.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.