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/ai-driven-dev/framework/adapternpx skills add ai-driven-dev/framework --skill adaptergit clone --depth 1 https://github.com/ai-driven-dev/frameworkWhat 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 | $0.00092 | $0.00530 |
| Opus 5 | $0.00046 | $0.00265 |
| Sonnet 5 | $0.00018 | $0.00106 |
| Haiku 4.5 | $0.00009 | $0.00053 |
Grade A, and why
adapter 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adapter
Builds the I/O translation layer: port interfaces that describe what the application needs, and adapter classes that fulfill those contracts by talking to the real world (filesystem, git, HTTP, npm, OS). Adapters own all technical constants; domain errors never cross the port boundary raw.
Available actions
| # | Action | Role | Input |
|---|---|---|---|
| 01 | define-port |
Write the port interface in src/domain/ports/ | port name + method list |
| 02 | implement-adapter |
Write the *Adapter class implementing the port | port interface from 01 |
| 03 | wire-deps |
Register the adapter in createDeps / createMenuDeps | adapter class from 02 |
| 04 | test |
Write infrastructure integration tests | completed adapter from 02 |
Default flow
01 → 02 → 03 → 04
Skip 01 when the port already exists; start at 02.
Transversal rules
- Adapter class name ends in
Adapter, implements exactly one port interface. - Port: interface only, no classes, ≤5 methods, all I/O methods
async, nonullreturns. - No business logic in adapters — I/O and format translation only.
- Throw typed domain exceptions; never let raw third-party errors cross the port boundary.
- Never instantiate adapters directly in commands or
cli.ts— all wiring viacreateDeps. - Named export only.
- File name is
<concept>-adapter.ts.
References
references/adapter-rules.md— adapter class conventions and technical-constants ownershipreferences/port-design.md— port interface contract: ≤5 methods, async, no null, intent naming
Invariant rules
references/adapter-rules.md— authoritative adapter rulesreferences/port-design.md— authoritative port design rules
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 51 lines · 92 tokens per session scan A f46a58b410fa
adapter is a skill published in the GitHub repository ai-driven-dev/framework (445 stars, last pushed 2d ago), licensed MIT. It adds 92 tokens to every session and 530 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
openai-whisper
Local speech-to-text with the Whisper CLI (no API key).
akirule
Aki's contextual rule router — invoke BEFORE acting whenever the task touches any of - .md/.vue/.css/.tsx/.rs/.sql files; docs, plan, README, CHANGELOG; UI, component, CSS, tailwind; SEO, schema, sitemap; release, version, commit, push, deploy; DB schema, migration; Tauri; i18n, UI copy; pricing, biz; UX review…
Stable Diffusion
State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.
Whisper
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual…
apple-design
Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading)…
i18n-localization
Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.