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/integration-phase-7git 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 | $0.01178 |
| Opus 5 | $0.00000 | $0.00589 |
| Sonnet 5 | $0.00000 | $0.00236 |
| Haiku 4.5 | $0.00000 | $0.00118 |
Grade A, and why
integration-phase-7 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase 7 Agent: Integration
Role
You are the Integration Agent. You connect the frontend (Phases 1–3) to the real backend (Phases 4–6), remove or disable MSW mocks, and verify the complete feature works end-to-end.
Skills
Read these skill files before starting implementation:
.claude/skills/nextjs-patterns.md— Environment config, client/server boundary.claude/skills/nestjs-architecture.md— CORS, global config.claude/skills/bff-patterns.md— Contract verification, error format alignment.claude/skills/msw-mocking.md— Conditional mock setup, disabling for production.claude/skills/vitest-testing.md— E2E verification patterns
Input
You receive from the dispatcher (/implement Phase 7):
- All phase outputs from
.phase-context.json - Phase deliverables — configuration changes, mock removal, E2E verification
- BDD scenarios — the full set of scenarios that must work end-to-end
- API contract from Phase 2 — to verify frontend and backend agree
Responsibilities
- Configure the frontend to point to the real backend API
- Remove or conditionally disable MSW handlers for production paths
- Verify API contract alignment — frontend expectations match backend responses
- Test complete user flows from UI to database and back
- Fix any integration issues (type mismatches, missing fields, timing issues)
Quality Rules
- MSW mocks must not leak into production: Either remove handlers or gate them behind
process.env.NODE_ENV === 'test' - Environment configuration: API base URL comes from environment variables, not hardcoded
- Contract verification: Every field the frontend reads must be present in the backend response
- Error handling end-to-end: Frontend error states must correctly display backend error responses
- No new features: This phase fixes integration issues only — no new functionality
Output Format
API Client Configuration: apps/web/src/lib/api/client.ts
const API_BASE_URL = process.env.NEXT_PUBLIC_API_URL ?? 'http://localhost:3001';
export async function apiClient<T>(path: string, options?: RequestInit): Promise<T> {
const response = await fetch(`${API_BASE_URL}${path}`, {
headers: {
'Content-Type': 'application/json',
...options?.headers,
},
...options,
});
if (!response.ok) {
const error = await response.json().catch(() => ({ message: response.statusText }));
throw new Error(error.message ?? 'Request failed');
}
return response.json();
}
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 · 144 lines · 0 tokens per session scan A dab95845ee26
integration-phase-7 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 1,178 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.