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/apache/datafusion-python/audit-skill-mdnpx skills add apache/datafusion-python --skill audit-skill-mdgit clone --depth 1 https://github.com/apache/datafusion-pythonWhat 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 | $0.00079 | $0.03134 |
| Opus 5 | $0.00039 | $0.01567 |
| Sonnet 5 | $0.00016 | $0.00627 |
| Haiku 4.5 | $0.00008 | $0.00313 |
Grade A, and why
audit-skill-md 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 yesterday.
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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit skills/datafusion_python/SKILL.md
You are auditing the user-facing skill at
skills/datafusion_python/SKILL.md
against the current state of the Python API. The skill is the source of truth
for how AI coding assistants are taught to write datafusion-python code, so
it must match what the project actually ships. This skill identifies gaps
caused by upstream syncs, refactors, or renames, and (if asked) applies the
edits directly to SKILL.md.
The skill is most usefully run after the check-upstream step of an
upstream sync (see dev/release/upstream-sync.md) — once any new APIs are
exposed, this skill makes sure they get documented.
What the skill covers
The user-facing SKILL.md documents these public surfaces. This list is not
exhaustive — if a new top-level area is added (e.g., a new Catalog API
exposed at the package root), include it.
| Surface | Module | Sections in SKILL.md |
|---|---|---|
SessionContext |
python/datafusion/context.py |
"Data Loading" |
DataFrame |
python/datafusion/dataframe.py |
"DataFrame Operations Quick Reference", "Executing and Collecting Results", "Idiomatic Patterns" |
Expr |
python/datafusion/expr.py |
"Expression Building", "Common Pitfalls" |
functions |
python/datafusion/functions/__init__.py |
"Available Functions (Categorized)", scattered uses throughout |
functions.spark |
python/datafusion/functions/spark.py |
"Available Functions (Categorized)" → "Spark-Compatible Functions" subsection |
Top-level helpers (col, lit, WindowFrame, ...) |
python/datafusion/__init__.py |
"Import Conventions", "Core Abstractions" |
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.
- yesterday First seen · 291 lines · 0 tokens per session scan A ce829783037b
audit-skill-md is a skill published in the GitHub repository apache/datafusion-python (598 stars, last pushed 2d ago), licensed Apache-2.0. It adds 79 tokens to every session and 3,134 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…