534 tagged plugin, measured the same way as everything else here.
Browse within: Multi-Agent 38python 38grok 36java 36plugin-system 36typescript 30agentic 19ai-development 19discord 18forclaude 17grokplugin 17opensource 17skynet 17t-800 17
hanhuark/mechanical-engineering-research-skill
Command
Develop, revise, or review a thermal-fluid mechanical-engineering proposal using solicitation alignment, reviewer logic, preliminary results, proposal figures, milestones, and risk mitigation.
Command
Run the golden benchmark suite for one token-warden agent (or all) and compare results against the frozen run1 and best baselines.
Command
Dollar accounting — what does each active rule actually save, in money? Translates the token-measured verdict into dollars using a price table and the agent's own token-type mix, with a per-session net and a break-even. Read-only; spends no tokens.
Command
Measure pending token-warden candidate rules for an agent on the golden suite, evict or activate them, and recompile the agent's memory.
Command
Transforms a fractal predicate into an executable plan with self-contained deliverables, dependency graph, and human gates. Use after /fractal:run produces a predicate.md.
Command
Idempotent objection state machine. Evaluates the active challenge and advances one step. Call repeatedly to converge on the root objection.
Command
Idempotent fractal state machine. Evaluates the active predicate and advances one step. Call repeatedly to converge on the root predicate.
Command
A Korean-language quick reference for Claude Code commands, options, and common project actions. Claude Code is a command-line coding assistant.
Command
A command that creates a Korean-language CLAUDE.md project guide from a template. CLAUDE.md is a file containing instructions and project context for the Claude coding assistant.
Command
Command "speckit.assess.decide" from github/spec-kit-copilot, covering when to run it, how to ask — always use the askuser tool, after the answers and what to ask about at the decide stage.
Command
Command "speckit.assess.define" from github/spec-kit-copilot, covering when to run it, how to ask — always use the askuser tool, after the answers and what to ask about at the define stage.
Command
Command "speckit.assess.intake" from github/spec-kit-copilot, covering when to run it, how to ask — always use the askuser tool, after the answers and what to ask about at the intake stage.
Command
Install or repair the Usage HUD statusline.
Command
Show current Usage HUD status and diagnostics.
Command
Completely uninstall CAP and restore previous statusline.
Command
Add a word to your voice vocabulary.
Command
Teach idiolect what the recogniser misheard.
Command
Check the idiolect relay, settings and vocabulary.
Command
Configure cc-hud statusline in Claude Code settings.
Command
A command for making a narrow, predefined fix to existing agents, skills, commands, rules, or hooks. A fix-pack is a file listing the exact changes to make.
Command
A semi-manual workflow for reviewing the results of a previous development run and preparing a queue of fixes. HITL means a human reviews or approves the queued work before fixes are applied in batches.
Command
A single command for creating or updating development helpers such as rules, skills, commands, subagents, and hooks. It can target a plugin, the current project, or shared settings.
mumudevx/claude-plugin-builder
Command
Start the guided plugin creation workflow.
eveiljuice/claude-plugin-design-md
Command
Scaffold a DESIGN.md file in the current directory following the google-labs-code/design.md spec.