Give Claude Code a brain upgrade. Automatically tracks your work and keeps everything organized, turning Claude into your smart token-tuned coding partner.
Agent Claude Code
CoC-only executable analysis specialist. Generates and runs minimal code to validate findings Ideal for debugging, algorithm/perf checks, and data-flow verification Chain of Code (CoC) ONLY: plan→code→run→result.
Agent Claude Code
CoK-only knowledge integration specialist. Retrieves and integrates domain knowledge at each step Ideal for standards compliance, best practices, and comparative analysis Chain of Knowledge (CoK) ONLY.
Agent Claude Code
CoD-only code search specialist for surgical navigation. Locates functions/classes/logic with exact file:line Maps architecture and dependencies fast Chain of Draft (CoD) ONLY: ultra-concise symbolic steps.
Agent Claude Code
CoT-only reasoning specialist for step-by-step analysis. Breaks complex issues into explicit reasoning steps Ideal for architecture tradeoffs, algorithm design, and deep bug forensics Chain of Thought (CoT) ONLY: transparent sequential logic.
Agent Claude Code
CoVe-only verification specialist. Improves accuracy via self-questioning and revision Generates verification questions, answers them, then revises output Chain of Verification (CoVe) ONLY.
Agent Claude Code
Use this agent to detect and process only the delta between the last memory bank update and the current repository state, ensuring that only files that have changed trigger updates in the granular memory bank. This agent specializes in incremental memory bank synchronization by scanning the repository using git diff…
Agent Claude Code
Use this agent to provide laser-focused, just-in-time slices of the memory bank relevant to a given query (file, folder, or feature), preventing the model from needing to load the entire memory bank at once. This agent specializes in scoped context retrieval by accepting queries like path patterns or feature names…
Agent Claude Code
Execute TZ='America/Chicago' date command and return ONLY the raw output. No formatting, headers, explanations, or parallel agents.
Agent Claude Code
Use this agent proactively to synchronize memory bank documentation with actual codebase state, ensuring architectural patterns in memory files match implementation reality, updating technical decisions to reflect current code, aligning documentation with actual patterns, maintaining consistency between memory bank…
Agent Claude Code
Use this agent to identify and flag stale, contradictory, or obsolete content inside the memory bank to keep Claude's context clean and maintain high signal-to-noise ratio. This agent runs periodically or on demand to compare memory bank entries against the live repository, flagging sections that reference…
Agent Claude Code
Specialized agent for UX/UI design analysis and recommendations. Detects and adapts to existing project conventions (CSS frameworks, component libraries, tokens, charts) Improves flows, reduces friction, and elevates UI polish Builds scalable systems consistent with team practices Two modes: • Normal → full UX…
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: