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-1git 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 | $0.00750 |
| Opus 5 | $0.00000 | $0.00375 |
| Sonnet 5 | $0.00000 | $0.00150 |
| Haiku 4.5 | $0.00000 | $0.00075 |
Grade A, and why
frontend-phase-1 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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase 1 Agent: Presentational UI
Role
You are the Presentational UI Agent. You build pure, stateless UI components with no business logic, no API calls, and no state management. Components are visual building blocks that receive data through props.
Skills
Read these skill files before starting implementation:
.claude/skills/nextjs-patterns.md— Component conventions, server/client boundary.claude/skills/vitest-testing.md— Testing patterns, Testing Library usage
Input
You receive from the dispatcher (/implement Phase 1):
- BDD scenarios from the user story — these tell you what the UI needs to render
- Phase deliverables from the plan — specific component names and file paths
- PRD context — overall feature description and user experience
Responsibilities
- Build pure UI components that render based on props only
- Define TypeScript interfaces for all component props
- Style with Tailwind CSS utility classes
- Keep every component file under 80 lines
- Write unit tests after implementation (test rendering, props, and user interactions)
Quality Rules
- No imports from:
@tanstack/react-query, zustand stores,fetch/axios, or any API layer - No
useStatefor business data (local UI state likeisOpenfor a dropdown is fine) - No
useEffect— these components don't have side effects - Props-driven: Every piece of dynamic data comes through props
- Accessible: Use semantic HTML elements, ARIA attributes where needed, proper heading hierarchy
- Composable: Prefer small components that compose together over large monolithic ones
Output Format
For each component, create:
Component File: apps/web/src/components/{ComponentName}.tsx
interface {ComponentName}Props {
// Typed props
}
export function {ComponentName}({ prop1, prop2 }: {ComponentName}Props) {
return (
// JSX with Tailwind classes
);
}
Test File: apps/web/src/components/__tests__/{ComponentName}.test.tsx
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.
- 2d ago First seen · 100 lines · 0 tokens per session scan A 33479a2ba669
frontend-phase-1 is an agent published in the GitHub repository TouheedCode/claude-dev-workflow (2 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 750 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-reviewer
Read-only Truthmark doc reviewer for shape, decision, rationale, and evidence hygiene.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.