Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From evolving-lite
Manages session startup by reading memory, orienting to context, announcing status, and supporting resume commands like 'continue'.
npx claudepluginhub primeline-ai/evolving-liteHow this skill is triggered — by the user, by Claude, or both
Slash command
/evolving-lite:system-bootThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
On every session start, perform this bootup sequence:
Reconstructs consistent AI agent identity after cold starts by progressively loading CLAUDE.md and MEMORY.md, detecting fresh vs continuation sessions, calibrating behavior, and verifying coherence. Use at session starts, after crashes, or inconsistencies.
Manages continuity between Claude Code sessions: saves summaries, decisions, pending tasks from JSONL logs and loads automatic briefings with SQLite-backed search.
Maintains awareness across sessions by spawning observer agents on start, loading homunculus identity/instincts/git history, greeting with context, and notifying evolution opportunities.
Share bugs, ideas, or general feedback.
On every session start, perform this bootup sequence:
Read ${CLAUDE_PLUGIN_ROOT}/_memory/index.json for:
active_project: Which project the user was working onlast_session: When the last session wasIf active_project is set, read ${CLAUDE_PLUGIN_ROOT}/_memory/projects/{active_project}.json for:
progress: Array of recent progress entriesnext_step: What was planned nextfailures: Known blockers or failuresBased on memory:
Output a compact status line:
Evolving Lite | Session {n} | Tier {tier} | {experience_count} experiences
Last: {last_progress_summary}
Next: {next_step}
If this is the first session ever (no progress), announce:
Evolving Lite v1.0 | First session | {prewarmed_count} pre-warmed experiences loaded
Ready to work. The system learns from your corrections automatically.
If the user hasn't specified what to work on, suggest the next_step from memory. Don't start multiple tasks - pick one.
When the user says "continue", "weiter", "weitermachen", "fortsetzen", or "resume":
${CLAUDE_PLUGIN_ROOT}/_memory/sessions/When a session ends naturally (user says goodbye, or Stop hook fires):