Command Claude Code
Mirror a just-saved native memory into the shared evolve store so it becomes shareable and auditable.
Self improving agents through iterations
This repository also configures its own agents. See what altk-evolve tells them →
Command Claude Code
Mirror a just-saved native memory into the shared evolve store so it becomes shareable and auditable.
Command Claude Code
Analyze saved trajectories and recall audit events offline to record whether recalled guidelines influenced completed sessions.
Command Claude Code
Publish a private guideline to a configured write-scope repo.
Command Claude Code
Apply data-retention rules to the local evolve store — flag or delete stale and unused memories and expired sessions (dry-run by default).
Command Claude Code
Save the current conversation as a trajectory JSON file in OpenAI chat completion format for analysis and fine-tuning.
Command Claude Code
Captures the current session's successful workflow and saves it as a reusable skill with SKILL.md and helper scripts.
Command Claude Code
Add a shared guidelines repo (read-scope subscription or write-scope publish target) to the unified repos list.
Command Claude Code
Pull the latest guidelines from every configured repo (read- and write-scope).
Command Claude Code
Convert a saved trajectory into a reusable agent skill (SKILL.md + supporting scripts) that future agents can invoke to skip rediscovered work. Use when a session captured a non-trivial workflow worth promoting from a free-text guideline to an executable skill.
Command Claude Code
Remove a repo from the unified repos list and delete its local clone.
Command Claude Code
Adversarial, reproduce-by-execution review of a GitHub PR (fan-out sub-agents, verify, draft review).
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: