SiriCardKit: Skill for Claude Code

.claude/skills/siri-card/SKILL.md

siri-card is a skill for Claude Code from krispuckett/SiriCardKit. It costs 84 tokens per session (1,930 once invoked), scanned A, original, MIT.

A set of rules for building interactive cards that appear in Siri on iOS 26 and later. These cards can show information and respond to actions inside Siri.

In plain words
What is it for?
Use it to add or change Siri cards such as daily briefings, using App Intents and snippet views.
Why use it?
It provides exact layout and rendering rules for Siri cards, reducing trial and error when the card looks wrong or behaves unexpectedly.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md.

This is krispuckett/SiriCardKit's own configuration. It tells Claude Code how to work on SiriCardKit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything SiriCardKit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to krispuckett/SiriCardKit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/krispuckett/SiriCardKit/main/.claude/skills/siri-card/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/krispuckett/SiriCardKit

Made for: Claude Code.

Wrote 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.

agentmods badge for siri-card

README.md
[![agentmods](https://agentmods.dev/badge/skills/krispuckett/siricardkit/siri-card/github.svg)](https://agentmods.dev/skills/krispuckett/siricardkit/siri-card)
Your own site
<a href="https://agentmods.dev/skills/krispuckett/siricardkit/siri-card"><img src="https://agentmods.dev/badge/skills/krispuckett/siricardkit/siri-card/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.

agentmods 80×15 button for siri-card

Your own site · 80×15
<a href="https://agentmods.dev/skills/krispuckett/siricardkit/siri-card"><img src="https://agentmods.dev/badge/skills/krispuckett/siricardkit/siri-card.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,930 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00084 $0.01930
Opus 5 $0.00042 $0.00965
Sonnet 5 $0.00017 $0.00386
Haiku 4.5 $0.00008 $0.00193

Measured 12d ago against content hash db388923a05c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

siri-card 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 12d 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.

.claude/skills/siri-card/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Building Siri snippet cards

These are the binding rules for interactive Siri snippet cards, extracted from a production app and paid for with device debugging time. When a rule here conflicts with your prior knowledge of App Intents, this file wins.

This skill is the portable form of SiriCardKit's AGENTS.md. If the project you are in contains an AGENTS.md with these rules, that file is canonical; read it and follow it. If it also contains Sources/CardKit/, that is the reference implementation: build there first, verify, then move files into the app target.

The recipe is a verdict

A block starting with // Siri card recipe is the design source of truth: the person tuned it by eye in the Card Lab. A recipe is an ORDERED LIST OF BLOCKS: line order is render order. Grammar:

  • One block per line, in order: eyebrow:, headline:, row: LABEL | value | unit, columns: LABEL | value || LABEL | value (two or three stat cells, value big with the label beneath), line: (the sentence), chip: (the state chip), note: (the footnote). An empty or absent value is an absent block.
  • Adjacency is layout: a chip: line directly after eyebrow: shares the eyebrow's line, trailing right. Anywhere else the chip is its own line.
  • primary: and secondary: form the wells block, which renders last wherever those lines appear.
  • accent: is 6 hex digits, then a material: block: finish: ink or finish: glass, ink: (6 hex digits, clamped to the dark register), and the dials (topOpacity, fadeEnd, fadeCurve, floor, corner, rim, wellDepth).
  • Unknown keys are skipped. The laws apply on the way in: one of everything except rows (four at most), first wins, wells pinned last. The chip wears the accent when one exists and the eyebrow drops to ink; that is decided, not configured. On the glass finish the accent renders darkened to hold on the light ground; the stored value is unchanged.

Bake its values into the card verbatim: the words as written, the block order as the layout, the material numbers as constants, the accent as the one accent. Do not "improve" a recipe's numbers or reorder its blocks. If a recipe value would break a rule below (a floor of 0 with text placed below fadeEnd, say), keep the recipe and adjust the layout, not the material. Anything still wearing [brackets] in the prompt is a question only the person can answer; ask.

Read the full file on GitHub · 144 lines

Changes

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.

  1. 12d ago First seen · 144 lines · 84 tokens per session scan A db388923a05c

Subscribe to this mod's changes

siri-card is a skill published in the GitHub repository krispuckett/SiriCardKit (57 stars, last pushed 18d ago), licensed MIT. It adds 84 tokens to every session and 1,930 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.

Related

Other skills, from other repositories

orca-emulator-android

Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or phone on Windows, Linux, or macOS: booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the…

stablyai/orca · 102 tokens

android-tombstone-symbolication

Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…

dotnet/skills · 176 tokens

dogfood

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.

callstack/agent-device · 55 tokens

winapp-maui

Package and sign .NET MAUI Windows apps with winapp, resolving the resizetizer manifest dependency. Use when packaging or signing a .NET MAUI Windows app, building a MAUI MSIX or signed unpackaged build in CI, or fixing 'manifest contains unresolved placeholders ($placeholder$)' errors from winapp package.

microsoft/winappCli · 71 tokens

react-native-ease-refactor

Scan for Animated/Reanimated code and migrate to EaseView.

appandflow/react-native-ease · 18 tokens

apple-search-ads

When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…

Eronred/aso-skills · 127 tokens