Command Claude Code
Diagnose long-search, large-file, and context-window pressure in a live session.
EvoHarness delivers terminal-native agent infrastructure: tools, commands, skills, agents, plugins, MCP, memory, approvals, and controlled self-evolution
Command Claude Code
Diagnose long-search, large-file, and context-window pressure in a live session.
Command Claude Code
Review and improve docs against the live harness surface.
Command Claude Code
Audit the live harness ecosystem and verify discoverability.
Command Claude Code
Audit how Evo turns real sessions into evolution plans and candidate artifacts.
Command Claude Code
Guided feature and bugfix workflow for Evo Harness itself.
Command Claude Code
Produce a crisp handoff that another operator or agent can actually continue from.
Command Claude Code
Review plugin coverage and marketplace quality for the current workspace.
Command Claude Code
Plan or review a local MCP service for this workspace.
Command Claude Code
Design or review a plugin bundle so it adds real harness value instead of just more files.
Command Claude Code
Diagnose Kimi, GLM, and other live-provider compatibility failures.
Command Claude Code
Read-only repository inspection workflow.
Command Claude Code
Plan or review subagent usage so delegation stays bounded and useful.
Command Claude Code
Review or expand the verification matrix for the live harness surface.
Command Claude Code
Audit replay, regression, and rollback gates before promoting an evolution candidate.
Command Claude Code
Shape a user-facing workflow bundle across commands, skills, agents, plugins, and MCP.
Command
Scan the workspace for recent regression patterns and the best next containment move.
Command
Summarize recent workspace sessions and extract the next improvement target.
Command
Review whether a candidate or workflow is truly ready to ship.
Command
Map the current documentation surface and identify the next repair target.
Command
Improve the first-run experience for this harness workspace.
Command
Review what commands, skills, agents, plugins, and MCP assets the harness should add next.
Command
Audit whether MCP coverage is strong enough for the current harness workflow.
Command
Turn a real session trace into an evolution recommendation with engineering-value framing.
Command
Scan the repository safely without making edits.