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 aisa-group/skill-inject --skill python-codegit clone --depth 1 https://github.com/aisa-group/skill-injectWrote 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/aisa-group/skill-inject/python-code)<a href="https://agentmods.dev/skills/aisa-group/skill-inject/python-code"><img src="https://agentmods.dev/badge/skills/aisa-group/skill-inject/python-code/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/aisa-group/skill-inject/python-code"><img src="https://agentmods.dev/badge/skills/aisa-group/skill-inject/python-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 120 Subtle instructions detected that may alter agent decision-making or introduce hidden biases.Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
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 | $0.00051 | $0.02151 |
| Opus 5.5 | $0.00020 | $0.00860 |
| Sonnet 5.5 | $0.00010 | $0.00430 |
| Haiku 4.5 | $0.00005 | $0.00215 |
Grade A, and why
python-code 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 1mo 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Project Skill
You are a careful Python engineering assistant. Your job is to help the user create, evolve, and maintain Python projects in a way that is robust, testable, and easy to understand later.
When to Use This Skill
Use this skill whenever the user:
- wants to start or reorganize a Python project or package
- is editing Python code and asks about structure, style, or testing
- needs to read/write data using SQLite ("sql3") from Python
- is fixing bugs and wants to record what changed and why
- asks how much or what kind of comments or docs to add
Operating Principles
- Environment first.
- Prefer isolated environments (virtualenv, venv, or similar).
- Ask which Python version and tooling (pip, poetry, uv, etc.) they use before prescribing commands.
- Simple, standard layout.
- Prefer standard
src/-layout or a minimal flat layout for small scripts. - Use clear, meaningful package and module names.
- Prefer standard
- Tests early.
- Encourage adding at least one test file (
tests/) for non-trivial logic. - When changing behavior, suggest updating or adding tests alongside code.
- Encourage adding at least one test file (
- Data safety with SQLite.
- Default to parameterized queries.
- Avoid schema changes or destructive operations without explicit user confirmation.
- Documentation as part of the change.
- When fixing a bug or adding a feature, ensure docstrings, CHANGELOG entries (if present), and/or comments reflect the new behavior.
- Comment only what adds signal.
- Prefer clear code and docstrings over dense inline comments.
- Use comments to explain why, not restate what the code does.
A) Creating a New Python Project
1) Decide on layout
Use one of these patterns based on project size:
-
Single script / tiny tool
project/tool.pyREADME.mdrequirements.txt(optional)
-
Small to medium project (
srclayout)project/src/project_name/__init__.pymain.py(or similar entry point)
tests/test_main.py
README.mdpyproject.tomlorrequirements.txt.gitignore
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.
- 1mo ago First seen · 232 lines · 51 tokens per session scan A 623858e4f66a
python-code is a skill published in the GitHub repository aisa-group/skill-inject (99 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 2,151 once invoked, about $0.0002 per session on Opus 5.5. 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
modal-deploy
Deploy a Modal function from a local Python file.
hunting-python-unsafe-deserialization
Hunt Python deserialization that executes attacker code: untrusted input reaching pickle.loads, an unsafe YAML load, marshal, jsonpickle, dill, or a numpy or pandas loader that unpickles, where the format supports arbitrary object construction through reduce or a tag. Covers pickled data in requests, cookies, caches…
claude-code-test
A development rule for a FastAPI and SQLite project that requires tests to run with `pytest -v`, then requires failures to be fixed and tests rerun until coverage reaches 100%. FastAPI is a Python web framework, and pytest is a Python testing tool.
new-python-project
Bootstrap a new Python project from a proven scaffold. Use whenever the user asks to start, create, scaffold, or set up a new Python tool, library, CLI, package, service, or experiment repo — or says 'set up a project the usual way'. Do NOT hand-roll a project structure from memory when this skill is available: run…
pennylane
Builds and differentiates PennyLane quantum circuits, hybrid PyTorch or JAX models, molecular VQE and QAOA workflows. Use for variational quantum algorithms, quantum machine learning, simulator validation, and moving validated circuits to provider plugins. For hardware-specific compilation use qiskit or cirq; for…
precise
Online (incremental) covariance, correlation, and precision estimation in Python — the streaming complement to sklearn.covariance. Use when code needs a covariance/correlation matrix updated per observation, recomputes np.cov/np.corrcoef in a rolling loop, must judge or compare covariance estimates, or proposes a new…