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 commands/colossus-lab/openarg_backend/new-endpointgit clone --depth 1 https://github.com/colossus-lab/openarg_backendWrote 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/commands/colossus-lab/openarg_backend/new-endpoint)<a href="https://agentmods.dev/commands/colossus-lab/openarg_backend/new-endpoint"><img src="https://agentmods.dev/badge/commands/colossus-lab/openarg_backend/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 | $0.00000 | $0.00534 |
| Opus 5 | $0.00000 | $0.00267 |
| Sonnet 5 | $0.00000 | $0.00107 |
| Haiku 4.5 | $0.00000 | $0.00053 |
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 4d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create new FastAPI endpoint: $ARGUMENTS
Add a new endpoint to the API. Follow these steps:
1. Create the router
Create src/app/presentation/http/controllers/{module}/{module}_router.py:
from fastapi import APIRouter
from dishka.integrations.fastapi import FromDishka, inject
from pydantic import BaseModel
router = APIRouter(prefix="/{module}", tags=["{module}"])
class {Module}Request(BaseModel):
field: str
class {Module}Response(BaseModel):
result: str
@router.post("/", response_model={Module}Response)
@inject
async def create_{module}(
body: {Module}Request,
service: FromDishka[IService],
) -> {Module}Response:
result = await service.execute(body.field)
return {Module}Response(result=result)
Reference: src/app/presentation/http/controllers/query/query_router.py (full example with DI, rate limiting, WebSocket), src/app/presentation/http/controllers/datasets/datasets_router.py (simple CRUD).
2. Add rate limiting (if needed)
from slowapi import Limiter
from slowapi.util import get_remote_address
limiter = Limiter(key_func=get_remote_address)
@router.post("/")
@limiter.limit("10/minute")
async def endpoint(request: Request, ...):
...
3. Define Pydantic schemas
Request/response models go in the same router file or a separate schemas.py if complex.
Conventions:
- Request:
{Name}Request - Response:
{Name}Response - Use
Field()with descriptions for OpenAPI documentation
4. Register in the root router
Edit src/app/presentation/http/controllers/root_router.py:
from .{module}.{module}_router import router as {module}_router
api_router.include_router({module}_router)
This mounts it under /api/v1/{module}/.
5. Inject dependencies
If the endpoint needs services/repos, make sure they're registered in Dishka (src/app/setup/ioc/provider_registry.py) and use FromDishka[InterfaceType] + @inject decorator.
Checklist
- Router created with endpoint(s)
- Pydantic schemas defined
- Rate limiting configured if public-facing
- Registered in
root_router.py - Dependencies available in Dishka
- Tested: endpoint responds correctly
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.
- 4d ago First seen · 80 lines · 0 tokens per session scan A 2d5679b8f7e5
new-endpoint is a command published in the GitHub repository colossus-lab/openarg_backend (144 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 534 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 2026-08-30.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.