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 opendatahub-io/ai-helpers --skill python-packaging-security-auditgit clone --depth 1 https://github.com/opendatahub-io/ai-helpersWrote 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/opendatahub-io/ai-helpers/python-packaging-security-audit)<a href="https://agentmods.dev/skills/opendatahub-io/ai-helpers/python-packaging-security-audit"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/python-packaging-security-audit/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/opendatahub-io/ai-helpers/python-packaging-security-audit"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/python-packaging-security-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.01518 |
| Opus 5.5 | $0.00021 | $0.00607 |
| Sonnet 5.5 | $0.00010 | $0.00304 |
| Haiku 4.5 | $0.00005 | $0.00152 |
Grade B, and why
python-packaging-security-audit scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf -- "${AUDIT_DIR}" Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Packaging Security Audit
Orchestrates a comprehensive pre-onboarding security evaluation of Python packages by dispatching three specialized sub-skills as parallel background agents. Each agent writes its report section to an individual file; the orchestrator reads all files and assembles the unified report.
Inputs
- repo_path (optional): Local filesystem path to an already-cloned repository
- package_name (optional): Python package name — the skill will locate and clone the repository
- hexora_results (optional): File path to pre-computed hexora JSON output
(
hexora-results.json). Forwarded to thepython-packaging-static-auditsub-skill. - binary_scan (optional): File path to pre-computed binary scanner JSON output
(
binary-scan.json). Forwarded to thepython-packaging-binary-auditsub-skill. - malcontent_results (optional): File path to pre-computed malcontent JSON
output (
malcontent-results.json). Forwarded to thepython-packaging-binary-auditsub-skill.
At least one of repo_path or package_name must be provided. If repo_path
is given and points to an existing directory, skip straight to Step 2. Otherwise,
use package_name to discover and clone the repository.
When pre-computed scan inputs are provided, repo_path is still needed for triage
context (reading source files to understand findings). Always use --depth 50
for cloning because the git-audit sub-skill runs its own git history commands
and needs sufficient commit history.
Step 1: Resolve Repository
If you already have a local repository path, skip to Step 2.
Otherwise, use the python-packaging-source-finder skill to locate the upstream repository URL:
Skill: python-packaging-source-finder
Args: <package_name>
If the skill returns a URL with high or medium confidence, clone it locally with enough history for the git scan:
CLONE_DIR=$(mktemp -d -t security-audit-XXXXXX)
git clone --depth 50 -- "<repository_url>" "$CLONE_DIR/repo"
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 · 173 lines · 52 tokens per session scan B 5f1e177c0890
python-packaging-security-audit is a skill published in the GitHub repository opendatahub-io/ai-helpers (38 stars, last pushed 2d ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,518 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
fastapi-templates
Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backend API projects.
temporal-python-testing
Test Temporal workflows with pytest, time-skipping, and mocking strategies. Covers unit testing, integration testing, replay testing, and local development setup. Use when implementing Temporal workflow tests or debugging test failures.
manimgl-best-practices
Trigger when: (1) User mentions "manimgl" or "ManimGL" or "3b1b manim", (2) Code contains from manimlib import , (3) User runs manimgl CLI commands, (4) Working with InteractiveScene, self.frame, self.embed(), ShowCreation(), or ManimGL-specific patterns. Best practices for ManimGL (Grant Sanderson's 3Blue1Brown…
ampl-installer
Expert in installing amplpy, AMPL modules (solvers), and license activation. Explains Community Edition, academic, trial, and commercial AMPL licenses. Use when setting up a new environment, pip/modules errors, license UUID, portal signup, Colab/Docker install, or which license fits your situation.
ampl-python
Expert in amplpy and Python integration with AMPL. Use when writing or refactoring amplpy scripts, notebooks, FastAPI services, data pipelines (pandas/polars), solver configuration via Python, result extraction, or Colab/MO-Book Python workflows. Knows amplpy.ampl.com and dev.ampl.com amplpy best practices.
python-patterns
Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.