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/cisco-open/ai-harness-toolkit/python-best-practicesnpx skills add cisco-open/ai-harness-toolkit --skill python-best-practicesgit clone --depth 1 https://github.com/cisco-open/ai-harness-toolkitWhat 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 | $0.00052 | $0.00549 |
| Opus 5 | $0.00026 | $0.00275 |
| Sonnet 5 | $0.00010 | $0.00110 |
| Haiku 4.5 | $0.00005 | $0.00055 |
Grade A, and why
python-best-practices 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 2d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Best Practices
Use this skill when reviewing or writing Python code that needs human-style engineering judgment: code smells, hot-path performance issues, test quality, and robust failure handling.
How To Use This Skill
Start by identifying the kind of Python work in front of you, then read only the matching reference files.
- Read
references/anti-patterns.mdwhen reviewing general code quality, maintainability, architecture smells, configuration handling, resource usage, or type-safety issues. - Read
references/performance.mdwhen the code is latency-sensitive, CPU-heavy, memory-heavy, uses async execution, or appears to sit on a hot path. - Read
references/testing.mdwhen reviewing test code, coverage quality, fixtures, mocking strategy, parameterization, or the structure of a pytest suite. - Read
references/error-handling.mdwhen reviewing validation, exceptions, failure modes, batch processing, recovery behavior, or API/service robustness.
Load more than one reference when the change crosses concerns. Examples:
- API handlers often need both
references/error-handling.mdandreferences/testing.md. - Async services often need both
references/performance.mdandreferences/anti-patterns.md. - Refactors of business logic and persistence boundaries often need both
references/anti-patterns.mdandreferences/error-handling.md.
Review Focus
Use the references to look for issues that mechanical tools often miss:
- brittle boundaries between I/O and business logic
- retries, timeouts, and configuration scattered through the code
- blocking work inside async flows
- tests that only cover happy paths or overuse mocks
- exceptions that lose context or hide partial failures
Do not inline the full guidance from the references into your response unless the user asks for it. Read the relevant file, apply it to the code at hand, and return concrete findings or edits.
Reference Map
references/anti-patterns.mdreferences/performance.mdreferences/testing.mdreferences/error-handling.md
What ships with it
4 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.
- 2d ago First seen · 50 lines · 52 tokens per session scan A b802dd3cef8b
python-best-practices is a skill published in the GitHub repository cisco-open/ai-harness-toolkit (12 stars, last pushed 6d ago), licensed Apache-2.0. It adds 52 tokens to every session and 549 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
bump-dependency
Bumps a Python package dependency across Home Assistant Core integrations, regenerates core requirement files, runs verification tests and prek lint, and prepares a pull request with proper release/compare links.
biopython
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use…
marimo-pair
Work inside the user's live marimo notebook from the code editor: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes through code mode. Use whenever you create, analyze, or improve the user's marimo notebook.
adk-style
Python style and codebase conventions for ADK (Agent Development Kit): private-by-default file visibility, imports, type hints, Pydantic v2 models, formatting, docstrings, logging, async I/O, file and test layout, and unit test structure. Use when writing or editing ADK source or tests, deciding whether a new file or…
coding
编写并运行 Python 代码，验证脚本逻辑和输出。.
ax-python-agent
Use when writing Python code with axllm for agents, child delegation, tools, MCP, citations, persistent playbook learning, stage instructions, runtime state, final typed responses, and direct-respond executor skipping.