From sundial-org-awesome-openclaw-skills-4
Preserves conversation continuity across token budget cycles by automatically archiving session history before compaction and restoring it on session restart.
How this skill is triggered — by the user, by Claude, or both
Slash command
/sundial-org-awesome-openclaw-skills-4:remember-all-prompts-dailyThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill maintains conversation continuity across token budget cycles by automatically archiving your session history before compaction and restoring it when a new session begins.
This skill maintains conversation continuity across token budget cycles by automatically archiving your session history before compaction and restoring it when a new session begins.
When token usage approaches 95%:
export_prompts.py to extract current session historymemory/remember-all-prompts-daily.md with date-wise entryWhen a new session starts (fresh 1% token usage):
memory/remember-all-prompts-daily.md exists# Remember All Prompts Daily
## [DATE: 2026-01-26]
### Session 1 (09:00 - 09:47)
[All prompts and responses from session]
### Session 2 (10:15 - 11:30)
[All prompts and responses from session]
scripts/export_prompts.pyExtracts all prompts/responses from current session and archives them.
Usage:
python scripts/export_prompts.py
What it does:
sessions_history() to fetch all messages from current sessionmemory/remember-all-prompts-daily.mdscripts/ingest_prompts.pyReads the daily archive and injects it as context on session start.
Usage:
python scripts/ingest_prompts.py
What it does:
memory/remember-all-prompts-daily.md (if exists)Add to HEARTBEAT.md to monitor token usage:
Check token usage - if >95%, export session history
For automatic triggers:
# Check token at regular intervals
clawdbot cron add --text "Check token usage and export if needed" --schedule "*/15 * * * *"
Session 1:
Session 2 (New Sprint):
python skills/remember-all-prompts-daily/scripts/export_prompts.py
cat memory/remember-all-prompts-daily.md | tail -100
python skills/remember-all-prompts-daily/scripts/ingest_prompts.py
Monitor token usage via:
session_status # Shows current token usage %
When you see token usage approaching 95%, the skill can auto-trigger, or you can manually export.
npx claudepluginhub sundial-org/awesome-openclaw-skillsManually saves important session context (decisions, facts, tasks) to a daily memory log without triggering native context compaction. Useful for explicit checkpoints on CLI or messaging channels.
Suggests manual context compaction at logical intervals via a pre-tool hook, preserving context through task phases rather than relying on arbitrary auto-compaction.
Suggests manual context compaction at logical intervals (e.g., after research, before implementation) to preserve task context, avoiding arbitrary auto-compaction during long sessions.