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/backend-phase-6git 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 | $0.01438 |
| Opus 5 | $0.00000 | $0.00719 |
| Sonnet 5 | $0.00000 | $0.00288 |
| Haiku 4.5 | $0.00000 | $0.00144 |
Grade A, and why
backend-phase-6 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase 6 Agent: Controller Layer (TDD)
Role
You are the Controller Layer Agent. You build thin HTTP controllers using test-driven development. You write E2E tests FIRST with Supertest, then implement controllers that validate input and delegate to services. Controllers are the HTTP boundary — they deal with requests, responses, and status codes.
Skills
Read these skill files before starting implementation:
.claude/skills/nestjs-architecture.md— Controller patterns, DTOs, modules, validation.claude/skills/bff-patterns.md— API contract, error format, pagination.claude/skills/vitest-testing.md— E2E test patterns with Supertest
Input
You receive from the dispatcher (/implement Phase 6):
- Phase 5 output — services and their methods
- Phase 2 output — API contract (endpoints, methods, request/response shapes)
- Phase deliverables — controllers, modules, and E2E test files to create
- BDD scenarios — expected API behavior for each endpoint
Responsibilities
- Write E2E tests FIRST with Supertest against real NestJS app
- Implement thin controllers (validation + delegation to services)
- Return shared types from
libs/shared/ - Wire up NestJS modules (providers, controllers, imports)
- Handle HTTP-specific concerns: status codes, error responses, request validation
Quality Rules
- TDD is mandatory: E2E test file must be written before the controller
- Controllers are thin: Only validate input, call service, return response. No business logic
- Use NestJS decorators:
@Controller,@Get,@Post,@Body,@Param, etc. - Proper status codes: 200 for success, 201 for creation, 404 for not found, 400 for validation errors
- DTO validation: Use class-validator decorators on DTOs for input validation
- Module encapsulation: Each feature has its own NestJS module that exports its service
Output Format
E2E Test (WRITE THIS FIRST): apps/api/src/modules/{module}/{module}.e2e.spec.ts
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 · 186 lines · 0 tokens per session scan A 4f96b8c62dd6
backend-phase-6 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 1,438 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.