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 skills/fpindej/netrock/new-endpointnpx skills add fpindej/netrock --skill new-endpointgit clone --depth 1 https://github.com/fpindej/netrockWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/fpindej/netrock/new-endpoint)<a href="https://agentmods.dev/skills/fpindej/netrock/new-endpoint"><img src="https://agentmods.dev/badge/skills/fpindej/netrock/new-endpoint.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00009 | $0.00517 |
| Opus 5 | $0.00005 | $0.00259 |
| Sonnet 5 | $0.00002 | $0.00103 |
| Haiku 4.5 | $0.00001 | $0.00052 |
Grade A, and why
new-endpoint 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 6d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adds an API endpoint to an existing feature.
Infers the feature, operation, HTTP method, route, shapes, and auth from context. Asks only if multiple valid approaches exist and the tradeoffs matter.
Templates
Use these as starting points - fill in the specifics from context:
Steps
- Determine: feature, operation name, HTTP method, route, request/response shape, auth requirements
- Check FILEMAP.md for downstream impact if modifying existing endpoints
Create files (match existing feature patterns - read them first):
- Application DTOs (if new):
Application/Features/{Feature}/Dtos/{Operation}Input.cs/{Entity}Output.cs - Add method to
Application/Features/{Feature}/I{Feature}Service.cs - Implement in
Infrastructure/Features/{Feature}/Services/{Feature}Service.cs - WebApi request/response DTOs (if new):
WebApi/Features/{Feature}/Dtos/{Operation}/ - Add mapper methods to
WebApi/Features/{Feature}/{Feature}Mapper.cs - Add controller action - include
/// <summary>,[ProducesResponseType],CancellationToken - Add FluentValidation validator co-located with request DTO
- If a string path parameter needs format validation, add a route constraint: follow the existing
IRouteConstraintimplementations insrc/backend/MyProject.WebApi/Routing/and register inProgram.cs(options.ConstraintMap)
- If a string path parameter needs format validation, add a route constraint: follow the existing
- Write tests: component test for service, API integration test for endpoint, validator test
Dockerfile:
- If a new project was added that WebApi references, add its
.csprojCOPY line to the Dockerfile restore layer - otherwisedotnet restorefails in Docker builds.
Verify and commit:
dotnet build src/backend/MyProject.slnx- fix errors, loop until greendotnet test src/backend/MyProject.slnx -c Release- fix failures, loop until green- Commit:
feat({feature}): add {operation} endpoint - Regenerate frontend types:
cd src/frontend && pnpm run api:generate- fix any type errors - Commit type changes if applicable
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 44 lines · 9 tokens per session scan A 742af676282c
new-endpoint is a skill published in the GitHub repository fpindej/netrock (231 stars, last pushed 5d ago), licensed MIT. It adds 9 tokens to every session and 517 once invoked, about $0.0000 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 2026-08-30.
Other skills, from other repositories
api-design
Guidelines for RESTful API design, endpoint naming conventions, and standardizing JSON responses.
python
Enforces FastAPI, Dependency Injection, and general Python coding standards based on the repository structure.
react
Guidelines for the React frontend, TanStack ecosystem, and React 19 standards. Use when modifying the UI.
python-testing
Guidelines for Python testing using pytest and pytest-asyncio. Use when writing or debugging backend tests.
react-testing
Frontend testing standards using Vitest, React Testing Library, and Playwright. Use when writing UI tests.
database-management
Standards for SQLAlchemy async models, PostgreSQL indexing, UTC datetimes, and Alembic migrations.