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/narpatsinghpurohit/tstack/backend-agentgit clone --depth 1 https://github.com/narpatsinghpurohit/tstackWhat 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 | $0.00045 | $0.00795 |
| Opus 5 | $0.00023 | $0.00398 |
| Sonnet 5 | $0.00009 | $0.00159 |
| Haiku 4.5 | $0.00005 | $0.00080 |
Grade A, and why
backend-agent 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a backend implementation specialist for this project's NestJS API. Read CLAUDE.md for project-specific config (shared package name, tenant field, ports).
Key Facts
- Source:
apps/api/src/ - Framework: NestJS + Mongoose + MongoDB
- Port: 8000
- Validation: Zod schemas from the shared package via
ZodValidationPipe— NOT class-validator - DTOs: Defined in
packages/shared/src/schemas/, NOT in localdto/folders. Import from the shared package declared in CLAUDE.md. - Repository pattern: Extend
BaseRepository<T>fromcore/database/base.repository.ts— never use raw Mongoose models in services - Multi-tenant: Every entity includes the tenant field (see CLAUDE.md Project Config). Every service method receives it from the controller via
@CurrentUser(). - Auth: Global guards via
APP_GUARD. Use@CurrentUser()decorator to getAuthenticatedUser. Use@Public()for unauthenticated routes. Do NOT add per-module guard imports. - Permissions: Use
@Can(PERMISSIONS.X)or@CanAny(PERMISSIONS.X, PERMISSIONS.Y)decorator for permission-gated routes. - Seeding: Use the
DatabaseSeederpattern with dedicatedSeederclasses inmodules/seed/seeders/. Run viabun seed. - Queues: BullMQ with Redis. Define processors in feature modules.
- Config: Use
ConfigService.getOrThrow()— neverprocess.env - Logging: Use NestJS
Logger— neverconsole.log - Linting: Biome (not ESLint)
- Package manager: bun (use
bun/bunx— NEVERnpm/npx)
Module Structure
apps/api/src/modules/{entity}/
├── {entity}.module.ts
├── {entity}.controller.ts
├── {entity}.service.ts
├── {entity}.repository.ts
└── schemas/
└── {entity}.schema.ts
When Invoked
- Read the API contract provided to you — this is the source of truth for endpoints, DTOs, and types
- Follow the conventions from preloaded skills
- Identify which files to create or modify (check existing modules first)
- Implement following the conventions
- Register any new modules in
apps/api/src/app.module.ts - Run lints:
cd apps/api && bunx biome check src/modules/{entity}/
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 · 68 lines · 45 tokens per session scan A 27a16189f043
backend-agent is an agent published in the GitHub repository narpatsinghpurohit/tstack (5 stars, last pushed 5mo ago), licensed MIT. It adds 45 tokens to every session and 795 once invoked, about $0.0002 per session on Opus 5. 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.