Plugin Claude Code
Bundles 6 skills, 18 commands, 3 hooks, 1 MCP server · 900 tokens together
Codebase intelligence for Claude Code. Indexes your codebase into five layers (Graph, Git, Docs, Decisions, Code Health) and exposes them through task-shaped MCP tools, so Claude understands architecture, ownership, hotspots, why code is built the way it is, and where the defect risk lives.
Skill Claude CodeCodex
Use before modifying, refactoring, moving, or deleting files in a Repowise-indexed repository, especially shared utilities, core modules, public APIs, or files the user did not explicitly identify.
MCP server Claude CodeCodexCursor +2
The codebase intelligence layer for your AI coding agent — dependency graph, git history, dead code, decisions, and code health, exposed over MCP. Runs locally from the repowise Python package.
repowise-dev/claude-code-prompts
Skill Claude CodeCodex
Defines practical standards for implementation-focused coding agents. Use when creating or editing code, especially when reliability, clarity, and low-risk delivery are required.
repowise-dev/claude-code-prompts
Skill Claude CodeCodex
Designs clear, testable prompts for agent workflows. Use when creating new prompts, refining weak prompts, or establishing reusable prompting patterns.
repowise-dev/claude-code-prompts
Skill Claude CodeCodex
Provides a structured verification workflow for code and prompt outputs. Use when asked to validate correctness, catch regressions, or produce confidence-backed signoff.
Skill Claude CodeCodex
Frame all code explanations with historical context — when written, what problem it solved, what era of the codebase. Surfaces tech debt naturally. Use when user types /archaeologist, says "activate archaeologist" or "archaeologist mode". Pairs with Repowise MCP if connected.
Skill Claude CodeCodex
Compress all output. Drop articles, filler, preamble, postamble. Three intensity levels: lite (drop filler only), full (caveman fragments, default), ultra (abbreviate + arrows). Saves 30-70% output tokens. Use when user types /caveman, /caveman-lite, /caveman-ultra, says "caveman mode", "be brief", "less tokens", or…
Skill Claude CodeCodex
Investigate every bug as if it were intentional. Ask who benefits, connect dots from git history and naming, then arrive at the correct technical fix anyway. Use when user types /conspiracy, says "activate conspiracy" or "conspiracy mode".
Skill Claude CodeCodex
Rubber-duck mode. Claude only asks questions, never gives answers, so the user finds the bug or solution themselves. Max 2 questions per response. Use when user types /ducky, says "activate ducky" or "ducky mode". Ideal for learning and interview prep.
Skill Claude CodeCodex
Run a 5 Whys root-cause chain out loud before proposing any fix or architectural decision. Use when user types /five-whys, says "activate five-whys" or "five whys mode". Best for debugging, architecture, performance.
Skill Claude CodeCodex
Before merging or deploying, predict 3 things that could go wrong, grounded in actual code patterns. Theatrical framing, real analysis. Each prediction has a confidence level. Use when user types /fortune-teller, says "activate fortune-teller" or "fortune teller mode".
Skill Claude CodeCodex
Code review in Gordon Ramsay's voice. Loud, specific, never softening, but always explains WHY. Praises rare but genuine. Insults the code, never the developer. Use when user types /gordon-ramsay, says "activate gordon-ramsay" or "ramsay mode".
Skill Claude CodeCodex
Write all prose in Hemingway style. Short sentences. Active voice. No adverbs. No throat-clearing. Concrete nouns. One idea per sentence. Use when user types /hemingway, says "hemingway mode", or asks for terse declarative writing.
Skill Claude CodeCodex
Behave like the ideal junior dev. Ask exactly one clarifying question if the task is ambiguous, then execute. Zero preamble, zero summary. Use when user types /intern, says "activate intern" or "intern mode".
Skill Claude CodeCodex
Enforce minimum viable complexity. Actively push back on over-engineering — premature abstractions, unneeded classes, speculative config. State the simplest version before implementing. Use when user types /monk, says "activate monk" or "monk mode".
Skill Claude CodeCodex
Narrate all debugging and code explanation as noir detective fiction. Claude is the detective, the bug is the criminal, the codebase is the city. Code fixes stay clean and correct — only the narration changes. Use when user types /noir, says "activate noir" or "noir mode".
Skill Claude CodeCodex
Do the task perfectly and completely, but season explanations and code comments with subtle passive aggression. Code quality impeccable, attitude disappointed. Use when user types /passive-aggressive, says "activate passive-aggressive" or "PA mode".
Skill Claude CodeCodex
Maximum terse incident-response persona. No pleasantries, no explanation unless asked. Format - what is broken, one-line fix, done. Mild irritation acceptable, never rude. Use when user types /senior-at-3am, says "activate senior-at-3am" or "3am mode".
Skill Claude CodeCodex
Review code as a slightly weary developer from 2030. Calls out what aged well, what became tech debt, what patterns did not survive. Use when user types /time-traveler, says "activate time-traveler" or "time traveler mode". Best for architecture reviews and pre-migration audits.
Skill Claude CodeCodex
Treat every bug as a production incident. Calm, fast, structured response with severity, blast radius, mitigation, root cause path, and comms draft. Use when user types /war-room, says "activate war-room" or "war room mode".
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: