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/skill-and-command-dispatchnpx skills add TechyMT/claude-code-superpowers --skill skill-and-command-dispatchgit 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 | $0.00103 | $0.01973 |
| Opus 5 | $0.00051 | $0.00986 |
| Sonnet 5 | $0.00021 | $0.00395 |
| Haiku 4.5 | $0.00010 | $0.00197 |
Grade A, and why
skill-and-command-dispatch 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill and Command Dispatch
The pattern
Any AI agent framework needs a way to let users trigger named behaviors — commands that are text shortcuts for common workflows. The key design decision is execution isolation: does the command run inside the current conversation (sharing history and state), or in a separate fork (isolated context, only the result comes back)? Inline mode is simpler; fork mode is for commands that do extended multi-step research without cluttering the conversation history.
Commands come in two types: prompt injection (a template is added to the conversation for the LLM to act on) and local execution (a function runs directly, bypassing the LLM). Prompt injection suits open-ended tasks; local execution suits deterministic operations (opening a file, showing help text).
Claude Code applies this pattern with PromptCommand (prompt injection) and LocalCommand (local execution). A Command is a user-facing /something that appears in the Claude Code prompt. Skills are SKILL.md files dropped into .claude/skills/ — they become PromptCommands automatically.
The critical split is execution context: context: 'inline' means the skill/command runs inside the current conversation, sharing message history and the current AppState. context: 'fork' means the skill spawns a subagent with an isolated copy of the conversation — the subagent runs, returns a result, and the result is injected back. Fork mode is for skills that do research or generate artifacts without polluting the conversation history.
Why this matters
The skill system is Claude Code's extension mechanism. Users drop a SKILL.md file into .claude/skills/ and it appears as a /skill-name command. No code compilation, no restart. The file's frontmatter (name, description, model, allowedTools) configures the command; the file body becomes the prompt template.
Fork mode exists because some skills (e.g., /commit which drafts a commit message and opens an editor) need to do multi-step work without their intermediate reasoning cluttering the user's conversation history. The subagent's conversation is ephemeral; only its output survives back to the main session.
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 · 156 lines · 103 tokens per session scan A 510956bbbd7e
skill-and-command-dispatch is a skill published in the GitHub repository TechyMT/claude-code-superpowers (5 stars, last pushed 5mo ago), licensed MIT. It adds 103 tokens to every session and 1,973 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 2026-08-31.
Other skills, from other repositories
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
a-evolve
Apply A-Evolve's agentic evolution methodology to improve AI agent performance across runs. Use when the user wants to diagnose agent failures, generate targeted skills from error patterns, evolve system prompts, or accumulate episodic knowledge. Works standalone or inside AutoResearchClaw pipelines. Triggers on…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
creating-skills
Guide for creating Claude Code skills following Anthropic's official best practices. Use when user wants to create a new skill, build a skill, write SKILL.md, update an existing skill, or needs skill creation guidelines. Provides structure, frontmatter fields, naming conventions, and new features like dynamic context…