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-git-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-git-audit)<a href="https://agentmods.dev/skills/opendatahub-io/ai-helpers/python-packaging-git-audit"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/python-packaging-git-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-git-audit"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/python-packaging-git-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 | $0.00041 | $0.01087 |
| Opus 5.5 | $0.00016 | $0.00435 |
| Sonnet 5.5 | $0.00008 | $0.00217 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade A, and why
python-packaging-git-audit scanned grade A with 2 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Network access**: `socket`, `urllib`, `requests.get`, `httpx` Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **Process spawning**: `subprocess`, `os.system`, `os.popen` How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Packaging Git Audit
Inspects the recent git history of a Python package repository for commits that modify supply-chain-sensitive files (setup.py, CI configs, .pth files, etc.) and contain suspicious patterns. Produces a self-contained "Git History Analysis" report section with triaged findings and a risk assessment.
Inputs
- repo_path (required): Local filesystem path to a git repository
- output_file (optional): Write the report section to this file path instead of
returning it inline. The first line of the file must be
RISK_RATING:<value>so the orchestrator can parse it without reading the full report.
Step 1: Enumerate Commits
Determine the number of commits available and scan up to the last 50:
git -C <repo-path> log -50 --format='%H'
Step 2: Filter Sensitive Files
From those commits, identify ones that modify supply-chain-sensitive files:
setup.py,setup.cfg,pyproject.toml,MANIFEST.in.github/workflows/*.yml,.gitlab-ci.yml- Any
.pthfiles __init__.pyfiles at package root
git -C <repo-path> log -50 --diff-filter=ACMR --name-only --format='COMMIT:%H|%aI|%ae' -- \
setup.py setup.cfg pyproject.toml MANIFEST.in \
'.github/workflows/*.yml' .gitlab-ci.yml \
'*.pth' '*/__init__.py'
Step 3: Search for Suspicious Patterns
For each flagged commit, extract the diff and search for suspicious patterns:
- Code execution:
eval(,exec(,compile( - Process spawning:
subprocess,os.system,os.popen - Encoding/serialization:
base64,marshal,pickle - Network access:
socket,urllib,requests.get,httpx - Native code:
ctypes,cffi - Embedded URLs:
http://,https://
git -C "<repo-path>" show --format= -m --first-parent "<commit>" -- "<file>" | \
grep -nE 'eval\(|exec\(|compile\(|subprocess|os\.system|os\.popen|base64|marshal|pickle|socket|urllib|requests\.get|httpx|ctypes|cffi|https?://'
Collect per finding: commit hash, author, date, file modified, and matching patterns.
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 · 116 lines · 41 tokens per session scan A b1869a43ac2e
python-packaging-git-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 41 tokens to every session and 1,087 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
block-no-verify-hook
Configure a PreToolUse hook to prevent AI agents from skipping git pre-commit hooks with --no-verify and other bypass flags. Use when setting up Claude Code projects that enforce commit quality gates.
turborepo-caching
Configure Turborepo for efficient monorepo builds with local and remote caching. Use when setting up Turborepo, optimizing build pipelines, or implementing distributed caching.
ainb-fleet:ainb-spawn
Spawn a coding-agent session correctly with ainb run: always into a git worktree, never bare into a plain checkout. Use whenever you are about to start a Claude/Codex/Gemini/Copilot session in a terminal. Guards the invocations that silently produce a (broken) workspace row, two agents sharing one working tree, a…
Finishing a Development Branch
Clean branch finalization, squashing commits, and updating changelogs before merging.