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/richardhe-fundamenta/practical-gcp-examples/python-runnernpx skills add richardhe-fundamenta/practical-gcp-examples --skill python-runnergit clone --depth 1 https://github.com/richardhe-fundamenta/practical-gcp-examplesWhat 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 | $0.00024 | $0.00252 |
| Opus 5 | $0.00012 | $0.00126 |
| Sonnet 5 | $0.00005 | $0.00050 |
| Haiku 4.5 | $0.00002 | $0.00025 |
Grade A, and why
python-runner 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.
What it actually says
python-runner
When the user asks for a computation or transformation:
- Write a short, self-contained Python script that prints its result to stdout.
- Call the
run_codetool with that script ascode. - Report the stdout back to the user as the answer.
Constraints (the sandbox enforces these structurally):
- No network access. Standard library only unless the runtime image provides a package.
- The script must
print()its text result — stdout is returned. - Files you write to the working directory are returned to the user as attachments; for binary results (images, etc.) write a file rather than printing bytes.
- Uploaded files are available by name (e.g.
open("data.csv")). Never hardcode or reconstruct a file's contents from memory — if a file you need isn't in the working directory, ask the user to attach it rather than inventing the data. - If run_code returns an error, read it, fix the script, and call run_code again.
- Keep scripts short and deterministic.
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 · 25 lines · 24 tokens per session scan A b7b613761426
python-runner is a skill published in the GitHub repository richardhe-fundamenta/practical-gcp-examples (54 stars, last pushed 16d ago), licensed MIT. It adds 24 tokens to every session and 252 once invoked, about $0.0001 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 2026-08-30.
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.