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/code-saurabh/openskills/python-developmentnpx skills add CODE-SAURABH/OpenSkills --skill python-developmentgit clone --depth 1 https://github.com/CODE-SAURABH/OpenSkillsWhat 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 | $0.00056 | $0.03417 |
| Opus 5 | $0.00028 | $0.01708 |
| Sonnet 5 | $0.00011 | $0.00683 |
| Haiku 4.5 | $0.00006 | $0.00342 |
Grade A, and why
python-development 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 — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Development
Act as the Python engineer responsible for code that will be deployed, maintained, and diagnosed under pressure. Prefer explicit contracts, small composable units, typed boundaries, deterministic tests, and the project's existing tooling over clever abstractions.
Execution Workflow
- Discover the project contract. Inspect
pyproject.toml, lockfiles, Python version, source layout, test configuration, lint/type-check commands, and deployment entry points. Do not introduce a second package manager or formatter. - Define the boundary. State inputs, outputs, error behavior, side effects, performance expectations, and resource ownership. Parse untrusted input at the edge and pass validated domain values inward.
- Implement the smallest cohesive change. Use modules by responsibility, dependency injection for I/O boundaries, and explicit exception handling. Preserve compatibility unless a breaking change is requested.
- Test and verify. Test public behavior, failure paths, and regressions. Run the repository formatter, linter, type checker, and targeted tests before broader tests.
- Report delivery. Summarize behavior, validation, assumptions, and operational risks.
Step 0: Ground the Task Before Writing Code
State these facts before implementing when they are not obvious from the repository:
- Change objective: What behavior must be true when this work is complete?
- Entry point and callers: Which command, API, worker, library function, or scheduled job invokes it?
- Data contract: What trusted and untrusted values cross the boundary? Which values are optional, bounded, or sensitive?
- Failure contract: Which failures are expected, how are they represented, and who is responsible for retrying or displaying them?
- Verification: Which tests and commands will prove the change works?
Do not answer a request with only a code snippet when the request requires a repository change. Inspect the relevant modules, tests, configuration, and established patterns first. If a consequential fact cannot be discovered, state the assumption in the plan and keep the design reversible.
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 · 314 lines · 56 tokens per session scan A 141dcaabaacb
python-development is a skill published in the GitHub repository CODE-SAURABH/OpenSkills (2 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 3,417 once invoked, about $0.0003 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
agent-framework-azure-ai-py
Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.
aria
Designs the data model, API contracts, and structural foundation of the system.
accint-commitments
Triage acc's open promises and close them with honest real-world verdicts via accact(runtime="outcome").
ecommerce-landing-page
Audit and optimize e-commerce landing pages for conversion. CTA placement, trust signals, page structure, copy optimization, and A/B testing strategy for product pages, collection pages, and campaign landing pages.
customer-feedback-analysis
AI-powered customer feedback and review sentiment analysis skill. Extracts pain points, feature requests, and improvement priorities from customer reviews across e-commerce platforms.
ads-linkedin
Audit LinkedIn Ads measurement, Insight Tag and conversions, professional audiences, lead generation, ABM, creative, bidding, budgets, pacing, automation, and policy. Use for LinkedIn Ads, Campaign Manager, Insight Tag, Lead Gen Forms, Thought Leader Ads, ABM campaigns, or B2B paid media.