superpowers
claudecodexCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Checks what AI coding agents change before it lands: impact analysis, architecture rules, and a tamper-evident record. MCP server plus 6 skills.
Plugin garuda from marketplace garuda in myshra777-ai/garuda. Commands read from the repo's manifest — today.
This plugin runs code on your machine — it starts local MCP servers. The exact commands are listed below; read them before installing.
architecture-reviewUse when asked to review a repository's architecture, check whether code follows documented layer or service boundaries, audit package coupling, or test ADR and AGENTS.md compliance. Garuda indexes the code into a call and import graph, extracts the rules written in ADRs, specs and agent instruction
change-impactUse before changing a function, interface, package or file, or when asked what breaks if something changes, who calls a symbol, or how risky an edit is. Garuda resolves the exact symbol, then reports its direct callers, transitive blast radius, the call chains that reach it, whether tests cover it a
evidence-verificationUse when someone asks you to prove that an architectural claim or requirement actually holds, verify a governance receipt, or export an audit trail. Garuda checks natural-language or ADR statements against the indexed code and returns each claim as supported, unverified or contradicted, with evidenc
post-edit-verificationUse after finishing a code change, and before committing or opening a pull request, to check that the edit introduced no new architectural or policy violations. Garuda re-indexes only the modified files, evaluates the git diff against configured YAML policies and ADR claims, and separates net-new vi
pre-edit-governanceUse before an AI coding agent modifies code, or whenever someone asks whether a planned change is safe to make. This is the mandatory checkpoint that runs first: in one call Garuda returns the target's caller fan-in, its criticality tier, the active YAML policies that apply, and the MUST and MUST NO
violation-repairUse after Garuda reports a BLOCK or REVIEW finding and you need to fix it without causing a second violation. Garuda returns the exact violating lines together with self-repair instructions, explains which policy or documented rule was broken and how the match was resolved, and lets you check a prop
garudaruns: garuda-mcp
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
AI-powered codebase understanding — analyze, visualize, and explain any project
9 skills · 10 agents · hooks
Editorial diagrams in your brand, as self-contained HTML and SVG. Architecture, flowcharts, sequence, state machines, ER and database schemas, timelines, swimlanes, org charts, Gantt, Wardley maps, user journeys, service blueprints, UML class, lifecycle phase maps, and charts from bar, line and scatter to Sankey, treemap and heatmap, plus many more. Redraws draw.io, Mermaid, Excalidraw and PlantUML files. Exports SVG and PNG.
1 skill · 7 commands
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.
3 skills · 6 commands · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.