agentmods.dev

Diffuse-Native-Apps: Skill for Claude Code

.agents/skills/add-capability/SKILL.md

add-capability is a skill for Claude Code, Codex from hoangsonww/Diffuse-Native-Apps. It costs 40 tokens per session (289 once invoked), scanned A, original, MIT.

A development guide for adding a new observable device capability to Diffuse. A capability is a named piece of device data, collected by platform-specific code, registered for supported platforms, and covered by tests.

In plain words
What is it for?
Use it to add a collector, capability identifier, schema, platform registry entry, or related tests, while recording the privacy level of every collected field.
Why use it?
It keeps new device data separate from the app's diff engine, storage, search, export, and screens. It also requires fake data in tests, so continuous integration does not need live hardware.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is hoangsonww/Diffuse-Native-Apps's own configuration. It tells Claude Code and Codex how to work on Diffuse-Native-Apps 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 Diffuse-Native-Apps configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./Scripts/format.sh.

not rated 11repo 1mo ago A scan 40 tokens original MIT
View source ↗ hoangsonww/Diffuse-Native-Apps hoangsonww.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to hoangsonww/Diffuse-Native-Apps. 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/hoangsonww/Diffuse-Native-Apps/master/.agents/skills/add-capability/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/hoangsonww/Diffuse-Native-Apps

Made for: Claude Code, Codex.

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 add-capability

README.md
[![agentmods](https://agentmods.dev/badge/skills/hoangsonww/diffuse-native-apps/add-capability/github.svg)](https://agentmods.dev/skills/hoangsonww/diffuse-native-apps/add-capability)
Your own site
<a href="https://agentmods.dev/skills/hoangsonww/diffuse-native-apps/add-capability"><img src="https://agentmods.dev/badge/skills/hoangsonww/diffuse-native-apps/add-capability/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 add-capability

Your own site · 80×15
<a href="https://agentmods.dev/skills/hoangsonww/diffuse-native-apps/add-capability"><img src="https://agentmods.dev/badge/skills/hoangsonww/diffuse-native-apps/add-capability.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 289 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.
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 $0.00040 $0.00289
Opus 5.5 $0.00016 $0.00116
Sonnet 5.5 $0.00008 $0.00058
Haiku 4.5 $0.00004 $0.00029

Measured yesterday against content hash 22632fa9ab41, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

add-capability 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.

.agents/skills/add-capability/SKILL.md · 31 lines

What it actually says

Add a capability

Read in order: Documentation/CapabilityGuide.md, Documentation/CollectorGuide.md, Documentation/adr/0002-capability-driven.md.

Create

  1. Capability ID and schema in Packages/DiffuseCapabilities (or the catalog the guide points at).
  2. A collector in Packages/DiffuseCollectors for each platform that can actually observe it. Do not pretend a Watch can enumerate Mac apps.
  3. A registry line on each platform that should expose it.
  4. Tests with a fake — never require live hardware in CI. Put API tests in Tests/Domain if the new type is public.

Do not touch

Adding a capability must not require edits to the diff engine, snapshot store, search, export, or app screens. If you are adding a SwiftUI view for one capability, stop.

Privacy

Every collected field needs public / local / sensitive / restricted. Restricted fields should not be collected. See skill privacy.

swift test --parallel
./Scripts/format.sh

If a golden fixture schema changed, skill fixtures.

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. yesterday First seen · 31 lines · 40 tokens per session scan A 22632fa9ab41

Subscribe to this mod's changes

add-capability is a skill published in the GitHub repository hoangsonww/Diffuse-Native-Apps (11 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 289 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-07.

Hardware and IoTTestingUnit testingandroiddevice-monitoringgradleiosipadosjetpack-compose
Related

add-capability compared with skills from other repositories

add-capability next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
add-capabilityhoangsonww/Diffuse-Native-AppsSkill111mo agoMITA40Claude Code, Codex
maui-unit-testingdotnet/maui-labsSkill235yesterdayMITA84Claude Code, Codex
motion-design-prokelvinkosbab/AppBootstrapAISkill8yesterdayMITA129Claude Code
android-adaptive-layout-prokelvinkosbab/AppBootstrapAISkill8yesterdayMITA147Claude Code
android-gradle-architecture-prokelvinkosbab/AppBootstrapAISkill8yesterdayMITA74Claude Code
r8-shrink-prokelvinkosbab/AppBootstrapAISkill8yesterdayMITA87Claude Code
xml-to-compose-migration-prokelvinkosbab/AppBootstrapAISkill8yesterdayMITA78Claude Code