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 skills add Sagargupta16/claude-skills --skill farm-stackgit clone --depth 1 https://github.com/Sagargupta16/claude-skillsWrote 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/sagargupta16/claude-skills/farm-stack)<a href="https://agentmods.dev/skills/sagargupta16/claude-skills/farm-stack"><img src="https://agentmods.dev/badge/skills/sagargupta16/claude-skills/farm-stack/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sagargupta16/claude-skills/farm-stack"><img src="https://agentmods.dev/badge/skills/sagargupta16/claude-skills/farm-stack.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00050 | $0.01864 |
| Opus 5.5 | $0.00020 | $0.00746 |
| Sonnet 5.5 | $0.00010 | $0.00373 |
| Haiku 4.5 | $0.00005 | $0.00186 |
Grade B, and why
farm-stack scanned grade B with 1 finding 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 2mo 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| Run as root in Docker | Add non-root user | How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FARM Stack Development Patterns
Quick Reference
| Task | Approach |
|---|---|
| New project | Use /scaffold-farm or follow structure below |
| Add feature | Create model -> service -> route (one file per domain per layer) |
| Config | Dual-layer: env vars (priority) + YAML fallback |
| Database | Motor async client, never sync PyMongo in routes |
| Docker | Alpine-based, compose with MongoDB + backend |
| Frontend | Vite + React, proxy API in dev, static mount in prod |
| Testing | pytest + httpx async, 80%+ coverage target |
Project Structure
project-root/
├── main.py # FastAPI entry with lifespan
├── requirements.txt # Pinned dependencies
├── pyproject.toml # Tool config (ruff, pytest)
├── .env.example # Environment template
├── Dockerfile # python:3.13-alpine
├── docker-compose.yml # MongoDB + backend + optional frontend
├── Makefile # Dev commands (run, test, lint, build)
├── config/
│ ├── __init__.py
│ ├── secrets_parser.py # Env + YAML config loader, Motor client
│ ├── secrets.yml # Local dev config (git-ignored)
│ ├── secrets.yml.example # Template with placeholders
│ └── logging.py # Logging setup
├── models/ # Pydantic v2 data models
│ └── {domain}_models.py # Base -> Create -> Response per domain
├── routes/ # API endpoint handlers
│ └── {domain}_routes.py # APIRouter per domain
├── services/ # Business logic layer
│ └── {domain}_services.py # Async MongoDB operations
├── utils/ # Shared utilities
├── tests/ # pytest suite
│ └── test_{domain}.py # Per-domain tests
├── client/ # React + Vite frontend
│ ├── package.json
│ ├── vite.config.js
│ └── src/
└── client_build/ # Built frontend (served as static)
Naming Convention
Domain files follow strict naming: {domain}_models.py, {domain}_services.py, {domain}_routes.py, test_{domain}.py.
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.
- 2mo ago First seen · 246 lines · 50 tokens per session scan B 6cc04a676825
farm-stack is a skill published in the GitHub repository Sagargupta16/claude-skills (5 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 1,864 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
farm-stack compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| farm-stackSagargupta16/claude-skills | Skill | 5 | yesterday | MIT | B | 50 | Claude Code |
| dynamicww-w-ai/bkit-claude-code | Skill | 605 | 12d ago | Apache-2.0 | A | 38 | Claude Code |
| solr-extendinggriddynamics/rosetta | Skill | 375 | yesterday | Apache-2.0 | A | 23 | Claude Code, Codex |
| fastapi-init-skilljiushiwon/wg-skills | Skill | 142 | yesterday | Apache-2.0 | A | 229 | Claude Code, Codex |
| ring:mapping-service-resourcesLerianStudio/ring | Skill | 218 | 11d ago | Apache-2.0 | A | 97 | Cursor |
| nodejs-init-skilljiushiwon/wg-skills | Skill | 142 | yesterday | Apache-2.0 | A | 219 | Claude Code, Codex |
| mongodb-atlas-webhookshookdeck/webhook-skills | Skill | 101 | yesterday | MIT | A | 89 | Claude Code, Codex |