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/techymt/claude-code-superpowers/domain-modelnpx skills add TechyMT/claude-code-superpowers --skill domain-modelgit clone --depth 1 https://github.com/TechyMT/claude-code-superpowersWhat 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 | $0.00075 | $0.01713 |
| Opus 5 | $0.00037 | $0.00856 |
| Sonnet 5 | $0.00015 | $0.00343 |
| Haiku 4.5 | $0.00007 | $0.00171 |
Grade A, and why
domain-model 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Domain Model
The pattern
A well-designed AI agent system separates three concerns: (1) capability objects — typed schemas declaring what the agent can do, with permission gates controlling access; (2) runtime injection — a context object passed to every capability invocation, carrying state, abort signals, and callbacks (so capabilities are independently testable, no global singletons); (3) atomic state — an immutable global store updated via reducer functions, so UI renders consistently and state transitions are traceable.
Claude Code names these: Tool (capability), ToolUseContext (injection), and AppState (state store). The other three concepts — Message, Task, and Command — complete the model: A Tool is a named capability with a typed input schema, a permission check, and an execution function. A Message is an immutable turn in the conversation — user input, assistant response, or system event. A Task is an optional background process that a tool can spawn. A ToolUseContext is the runtime environment injected into every tool call — it carries state, abort signals, callbacks, and configuration. AppState is the mutable global state store that the UI and tools read from and write to. A Command is a user-facing slash command that resolves to either a prompt template (injected into the conversation) or a local function.
Without understanding these six, you will model Claude Code incorrectly — treating it as a plain CLI instead of a React-driven state machine with a structured capability system.
Why this matters
Claude Code must bridge an LLM (which communicates via structured JSON tool calls) with a local developer environment (file system, shell, git). The Tool abstraction provides a single contract: the LLM produces a tool_name + input JSON block, the runtime validates the input against a Zod schema, checks permissions, and calls tool.call(). The result is returned to the LLM as a tool result block.
The ToolUseContext solves a layering problem: tools need access to state, permissions, callbacks, and configuration without those being global singletons. Every tool call receives the full context, making tools independently testable and the dependency graph explicit.
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.
- 2d ago First seen · 134 lines · 75 tokens per session scan A ff0a1f3b29d2
domain-model is a skill published in the GitHub repository TechyMT/claude-code-superpowers (5 stars, last pushed 5mo ago), licensed MIT. It adds 75 tokens to every session and 1,713 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 2026-08-31.
Other skills, from other repositories
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
ljg-learn
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or…
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
pedagogy-review
Holistic pedagogical review of a lecture deck (.qmd or .tex). Checks narrative arc, prerequisite assumptions, worked examples, notation clarity, and deck-level pacing. Use when user says "pedagogy review", "does this teach well?", "is the flow right?", "will students follow?", "review the narrative", or before…
master-yinguang
Use when user asks about 印光大师, 净土, 念佛, 持名念佛, 十念法, 摄耳谛听, 老实念佛, 信愿行, 带业往生, 仗佛慈力, 自力他力, 竖出横超, 往生, 极乐, 阿弥陀佛, 净土三经, 敦伦尽分, 闲邪存诚, 因果报应, 文钞, 一函遍复, or wants teaching in 印光大师 Yinguang's voice. Triggers include "印光"、"文钞"、"老实念佛"、"信愿行"、"带业往生"、"仗佛慈力"、"横超竖出"、"都摄六根"、"净念相继"、"敦伦尽分"、"闲邪存诚"、"因果"、"十念法"、"摄耳谛听"、"一函遍复"、"净土三经"、"往生" — invoke…