Superpowers: Brainstorming
claude.com/plugins/superpowersHere is exactly how it works
The brainstorming phase forces real design thinking before code
The /brainstorm skill makes Claude stop and have a back-and-forth conversation about what you are actually trying to build. It explores options, presents alternatives, and refines the concept with you before anything gets written.
It produces real artifacts before implementation starts
Once brainstorming is done and you have agreed on the direction, it outputs a design.md and a plan.md. Actual documents that capture the decisions made and the implementation roadmap. That means you have a paper trail of why things were built a certain way, and Claude has a concrete plan to execute against rather than freestyling.
The clean transition into implementation mode keeps things disciplined
Instead of brainstorming and coding getting tangled together (which is Claude Code's default tendency), Superpowers draws a hard line: you are either designing or you are implementing. Once you switch to implementation, you choose between two styles:
Agent-Eval
Internal Tool of AV EngineHere is exactly how it works
.agent folder: skills, memory, plugins, system prompt, tools. This is where the actual optimization happens. Why this matters
Most people fine-tune models or tweak prompts by feel. Agent-Eval turns that into a measurable, repeatable loop. Every improvement is backed by data. Every regression is caught before it ships. The model gets better every single day without any manual intervention.
Lossless Claw
github.com/Martian-Engineering/lossless-clawHere is exactly how it works
Current context management is destructive
OpenClaw, like most AI coding agents, uses a sliding-window approach that simply truncates older messages when the context window fills up. This means decisions, file changes, and reasoning from earlier in a session are permanently lost from the model's view. Lossless Claw replaces that entirely.
Agents can actively recall compressed history
It is not just passive summarization. The plugin gives agents tools like lcm_grep (search across all past messages and summaries), lcm_describe (inspect any summary or stored file), and lcm_expand_query (delegate a sub-agent to search the memory and answer a specific question from compacted history). An agent working on a long task can pull back exact details that would have been thrown away under normal compaction.
It solves the large-file context problem
When someone pastes a big file into a conversation, it can eat most of the context window in one shot. Lossless Claw intercepts files over a configurable threshold (default 25k tokens), stores them on disk, and replaces them with a compact exploration summary. The full file is always accessible. It just does not burn your context window.
- lcm_grep: Search across all past messages and summaries. Find any decision or file change from hours ago in seconds.
- lcm_describe: Inspect any summary or stored file without pulling it into the active context window.
- lcm_expand_query: Delegate a sub-agent to search the full compacted memory and answer a specific question. The most powerful tool in the set.
The compounding effect
Without Lossless Claw, long sessions degrade. The model forgets what it did 30 minutes ago. With it, sessions can run for hours and the agent still has access to everything it has ever seen. That is the difference between a tool that helps you code and a tool that thinks alongside you.
25 Prompts That Replace 25 Hours of Work
The exact prompts I use daily, packaged for you. Drop your email and it is yours.