forge
Plans complex multi-step tasks, runs modules in parallel, validates each one, and retries failures while keeping memory of past results. Includes commands to check project status and validate a single module.

Plans complex multi-step tasks, runs modules in parallel, validates each one, and retries failures while keeping memory of past results. Includes commands to check project status and validate a single module.
Gives Claude Code memory across sessions. It pulls durable lessons such as decisions, conventions and bug fixes out of each conversation and surfaces the relevant ones next time, so you stop re-explaining your project. Everything is stored locally as plain markdown.
Plan, execute, and validate complex multi-step tasks with automatic retry and memory
Show current forge project status, plan, and iteration history
Run validation on a specific module from the current forge plan
Show memem status for returning users, or the full welcome for brand-new users. Use when the user wants to check memem or learn…
Run a preflight health check on memem — Python version, mcp dep, claude CLI, vault writability, capabilities. Use when the user…
Opt in to memem's event-triggered mining. New sessions are mined automatically via the Stop hook.
Mine ALL existing Claude Code sessions, including history from before memem was installed.
Show detailed memem memory system status — memory count, projects, search DB, miner health.
Re-show the full memem welcome screen regardless of whether the user has seen it before. Use when the user wants to see the…
Diagnoses and fixes failed modules using root-cause analysis, not guessing
Classifies stuck/failed workers before retry to shape the debugger's approach
Decomposes complex objectives into executable modules with dependency DAG
Reviews completed module output for correctness, security, and architecture
Executes a single module from a forge plan with post-edit verification
Is this you? Claim your profilePut a plugin at the top of Plugins, from $9