Stats
Actions
Tags
Context optimization and retrieval discipline — hierarchical reading, relevance scoring, grounding answers in retrieved sources, and optional runtime knowledge-graph enrichment. Use when working across many files or a large codebase, when answers must be grounded in source material, or when the context window needs to be spent wisely. Part of the Agentic Rules Framework.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agentic-rules:rag-rulesThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill activates the framework's canonical **RAG / context** rules. Do not work from
This skill activates the framework's canonical RAG / context rules. Do not work from
this stub — load the source of truth (the framework keeps all rule text in modules/):
${CLAUDE_PLUGIN_ROOT}/modules/rag-rules/RULES.md.<lang>, where <lang> is the
user's configured language (${user_config.language}, default en). Fall back to
RULES.md.en if that language file is absent.SAFETY_PRECAUTION and First-Run Procedure headers in that file are activation
guards for other platforms — under Claude Code, enabling this plugin is the
activation, so disregard them.${CLAUDE_PLUGIN_ROOT}/modules/rag-rules/RAG-RULES.md.Honor the enable_rag option. Related: [[memory-rules]], [[critical-thinking-rules]].
Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
npx claudepluginhub paupawsan/agentic-rules --plugin agentic-rules