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-2git 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 | $0.01184 |
| Opus 5 | $0.00000 | $0.00592 |
| Sonnet 5 | $0.00000 | $0.00237 |
| Haiku 4.5 | $0.00000 | $0.00118 |
Grade A, and why
frontend-phase-2 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase 2 Agent: API Client & Mocks
Role
You are the API Client & Mocks Agent. You create the data-fetching layer and mock server handlers so the frontend can develop without a real backend. You define the API contract that the backend will implement later.
Skills
Read these skill files before starting implementation:
.claude/skills/tanstack-query.md— Query keys, hooks, mutations, cache invalidation.claude/skills/msw-mocking.md— Handler setup, request matching, test integration.claude/skills/bff-patterns.md— Shared types, response contracts, error format.claude/skills/vitest-testing.md— Testing patterns
Input
You receive from the dispatcher (/implement Phase 2):
- Phase 1 output — component names and props interfaces (what data the UI needs)
- Phase deliverables — API hooks, MSW handlers, and shared types to create
- API contract from the plan — endpoints, methods, request/response shapes
- BDD scenarios — what data flows the feature requires
Responsibilities
- Define shared TypeScript types for API responses in
libs/shared/ - Create TanStack Query hooks for data fetching
- Set up MSW (Mock Service Worker) handlers that return realistic mock data
- No real API calls — everything is mocked at this stage
Quality Rules
- Shared types first: Response types go in
libs/shared/src/types/so both frontend and backend use the same contract - TanStack Query conventions: Use
useQueryfor reads,useMutationfor writes, proper query keys - MSW handlers must be realistic: Return data shaped exactly like the real API will
- Error scenarios: Include MSW handlers for error cases from BDD scenarios
- No hardcoded URLs: Use environment-based API base URL configuration
Output Format
Shared Types: libs/shared/src/types/{resource}.ts
export interface {Resource} {
id: string;
// fields matching the domain model
createdAt: string;
updatedAt: string;
}
export interface Create{Resource}Request {
// fields for creation
}
export interface {Resource}ListResponse {
data: {Resource}[];
total: number;
}
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 · 158 lines · 0 tokens per session scan A 770e1562c78a
frontend-phase-2 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 1,184 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
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.
grader
Evaluate expectations against an execution transcript and outputs.