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/ffi-capsule-protocolnpx skills add apache/datafusion-python --skill ffi-capsule-protocolgit 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 | $0.00102 | $0.02290 |
| Opus 5 | $0.00051 | $0.01145 |
| Sonnet 5 | $0.00020 | $0.00458 |
| Haiku 4.5 | $0.00010 | $0.00229 |
Grade A, and why
ffi-capsule-protocol 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FFI Capsule Protocol
datafusion-python shares Rust objects with extension libraries through
PyCapsules. Every hook is a dunder method named __datafusion_<thing>__ that
returns a capsule wrapping an FFI-safe struct. They are one protocol, not a
collection of unrelated methods, and they have a settled convention that has
already been migrated once (see docs/source/user-guide/upgrade-guides.md,
DataFusion 52.0.0 and 55.0.0).
Rule 1 — enumerate the family before you change a member
Do this first, every time. It takes one command and it is the whole point of this skill:
grep -rn "__datafusion_[a-z_]*__" --include="*.rs" crates/ examples/*/src/
Compare the signature you are about to write against what the others already do. If yours is shaped differently, that is a finding about your design, not about theirs.
Rule 2 — a getter takes the session it is being installed on
fn __datafusion_physical_extension_codec__<'py>(
&self,
py: Python<'py>,
session: Bound<'py, PyAny>,
) -> PyResult<Bound<'py, PyCapsule>> { ... }
The host calls the getter and passes itself. That argument is how an extension library reaches things only the session has.
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 · 191 lines · 102 tokens per session scan A 0fbf0b020c1d
ffi-capsule-protocol is a skill published in the GitHub repository apache/datafusion-python (598 stars, last pushed 2d ago), licensed Apache-2.0. It adds 102 tokens to every session and 2,290 once invoked, about $0.0005 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…