Command
adversarial-review
Adversarial, reproduce-by-execution review of a GitHub PR (fan-out sub-agents, verify, draft review)
@agenttoolkitView CommandDevelopment
Command
/evolve-lite-publish
Publish a private guideline to a configured write-scope repo.
Install
> /plugin marketplace add AgentToolkit/altk-evolve > /plugin install evolve-lite@evolve-marketplace
How it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/evolve-lite-publish
Context preview
What this command does when you run it.
Publish a private guideline to a configured write-scope repo.
Command definition
evolve-lite-publish.mddescription: Publish a private guideline to a configured write-scope repo.
Use the `evolve-lite-publish` skill on the current conversation. Follow the skill's instructions exactly.
Ships withaltk-evolve
Coding agents repeat the same mistakes because they start fresh every session. Evolve gives agents memory — they learn from what worked and what didn't, so each session is better than the last.
Get the whole plugin
Stats
112
Stars
15
Forks
Active
Maintenance
Python
Language
Apache-2.0
License
10h ago
Last commit
9mo ago
Created
Repo: AgentToolkit/altk-evolve
Other commands on altk-evolve.
@agenttoolkitView CommandCommand
evolve-lite-adapt-memo…
Mirror a just-saved native memory into the shared evolve store so it becomes shareable and auditable
@agenttoolkitView CommandCommand
evolve-lite-provenance
Analyze saved trajectories and recall audit events offline to record whether recalled guidelines influenced completed sessions.
@agenttoolkitView CommandCommand
evolve-lite-retention
Apply data-retention rules to the local evolve store — flag or delete stale and unused memories and expired sessions (dry-run by default)
@agenttoolkitView CommandCommand
evolve-lite-save-traje…
Save the current conversation as a trajectory JSON file in OpenAI chat completion format for analysis and fine-tuning
@agenttoolkitView CommandCommand
evolve-lite-save
Captures the current session's successful workflow and saves it as a reusable skill with SKILL.md and helper scripts
@agenttoolkitView Command