superpowers
claudecodexCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Build and query an offensive security knowledge map through an MCP server and agent skills.
Plugin argos from marketplace argos-marketplace in rafabd1/Argos. Commands read from the repo's manifest — 24 days ago.
This plugin runs code on your machine — it starts local MCP servers. The exact commands are listed below; read them before installing.
adaptive-fuzzingUse feedback-led fuzzing to learn a specific parser, protocol, state machine, or sink boundary rather than replay generic payload lists. Use when code reading cannot settle input behavior or subtle transformations may expose new graph relations.
argosBuild, query, and revise an Argos knowledge graph during deep security research. Use when mapping a target, recovering prior knowledge, recording components or sinks, linking evidence, revisiting conclusions, finding blind spots, or exploring chains.
chain-discoveryDevelop realistic, non-obvious security chains from Argos sinks, side effects, authority transitions, state, and indirect graph paths. Use when a primitive needs impact elevation or the map contains related sinks that have not been tested together.
codebase-mappingMap a security-relevant codebase area into canonical Argos components, flows, authority, state, guarantees, and sinks. Use when entering a new subsystem, tracing a candidate, or repairing an incomplete target map.
evidence-testingDesign and record exact security tests that separate observation from inference and keep conclusions within proven path and condition limits. Use for hypotheses, negative controls, regressions, boundary checks, and conclusions that may need reopening.
exploit-validationValidate a security hypothesis as a realistic exploit, raise its impact through natural chains, and reject lab-assisted or forced scenarios. Use before treating an Argos hypothesis as a finding or when a primitive needs a credible PoC.
external-intelGather current, source-backed security and implementation context for Argos nodes, including expected behavior, upstream code, advisories, fixes, versions, and duplicate risk. Use before deep investment and whenever old knowledge may have changed.
finding-reportWrite a concise vulnerability report for an external triager from validated Argos knowledge and a supplied template. Use after exploit validation or when revising report wording, impact, or reproduction steps.
/argos:argosBuild or continue an Argos target knowledge map.
argosruns: node ${CLAUDE_PLUGIN_ROOT}/scripts/argos-mcp.cjs
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Scaffold, validate, and publish new Claude Code plugins with proper structure
3 skills · 1 command · 1 agent
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
Use Alibaba Open Code Review from local Codex.
2 skills
Claude Code skill for creating and presenting Slidev slidedecks
1 skill
Code intelligence powered by a knowledge graph. Provides execution flow tracing, blast radius analysis, and augmented search across your codebase.
12 skills · 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.