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/jaansokk/cursor_tools/python-devnpx skills add jaansokk/cursor_tools --skill python-devgit clone --depth 1 https://github.com/jaansokk/cursor_toolsWhat 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 | $0.00031 | $0.00677 |
| Opus 5 | $0.00015 | $0.00338 |
| Sonnet 5 | $0.00006 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
python-dev 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Conventions
Stack choices
- FastAPI — async endpoints, dependency injection via
Depends(), lifespan events - Pydantic v2 — schemas at all boundaries,
ConfigDict(from_attributes=True)for ORM models - SQLAlchemy 2.0 —
select()style,Mapped[],mapped_column(). No legacy 1.x Query API - Alembic — async migrations, always review autogenerated output
- pytest + pytest-asyncio + httpx AsyncClient for testing
Coding standards
- Async-first — all I/O (DB, HTTP, LLM) must be async. No blocking calls in async paths
- Type hints everywhere — modern Python syntax (PEP 604 unions, generics)
- Pydantic at all boundaries — no raw dicts across module boundaries
- Separate request and response models — don't reuse the same schema for both
- Structured logging — use the project's logging setup, not bare
print() - Meaningful errors —
HTTPExceptionwith correct status codes and clear messages - Small, focused functions — single responsibility
Architecture
- Business logic lives in service modules, not in endpoint functions
- Endpoints: validate input, call services, return responses
- Use
Depends()for sessions, config, auth, services - Group by feature/domain when the project grows, not by layer
- Use
lazy="selectin"or explicit eager loading to avoid N+1 queries - One session per request via dependency injection
Testing
- Test behavior: inputs, outputs, status codes, side effects
- Use fixtures for shared setup — organize
conftest.pyby scope - Mock external dependencies (LLM calls, external HTTP). Never hit real services in tests
- Cover: happy path, validation errors (422), auth failures (401/403), not-found (404)
Workflow
- Orient before coding — read existing code in the area, match patterns and naming conventions
- Small, focused changes — stay within scope, don't refactor unrelated code
- Write tests alongside implementation — new endpoints and services should ship with tests
- Validate after edits — run type checker and linter, run tests if they exist in the area
- If you change database models, create a new Alembic migration revision
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 · 57 lines · 31 tokens per session scan A d2398063adf3
python-dev is a skill published in the GitHub repository jaansokk/cursor_tools (1 stars, last pushed 5mo ago), licensed MIT. It adds 31 tokens to every session and 677 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 skills, from other repositories
ab-testing-framework
Design, run, and analyze A/B tests (controlled experiments) using Ronny Kohavi's methodology and Gibson Biddle's DHM trade-off analysis. Use when the user needs to plan an experiment, choose metrics (OEC), evaluate statistical significance, assess sample size requirements, avoid common experimentation pitfalls, or…
continuous-discovery
Guide teams through building sustainable customer interview habits and discovery practices. Use when setting up weekly customer interviews, preparing interview guides, coaching story-based interviewing technique, synthesizing user research findings, planning assumption tests, or helping teams that say they don't have…
prd-writer
Guide users through writing Product Requirements Documents (PRDs) and decomposing them into executable technical tasks. Use when creating a PRD, product spec, product one-pager, feature brief, PRP, or when breaking requirements into tasks with estimates, sprint planning, or technical decomposition.
product-led-growth-playbook
Evaluate growth strategy, growth team structure, and go-to-market motions using Elena Verna's PLG frameworks. Use when the user asks about product-led growth, PLG, growth team hiring, self-serve vs sales-led motions, product-led sales, PQA/PQL models, growth loops, when to hire a head of growth, earned vs rented…
ai-evals-builder
Build AI evals using the Husain-Shankar framework (error analysis, open/axial coding, LLM-as-judge). Use when a user needs to create, improve, or debug evals for an AI product — including defining failure modes, building LLM judges, or setting up production monitoring for an LLM application.
dhm-strategy-framework
Evaluate and strengthen product strategy using Gibson Biddle's DHM framework (Delight, Hard-to-copy, Margin-enhancing). Use when the user asks about product strategy, competitive advantage, feature prioritization trade-offs, or wants to stress-test whether a product idea is strategically sound.