After tick-hour, read .source.jsonl, apply the host-switch filter, write summary and saliency. Edition A (host CLI) or B (API key). Does not touch the snapshot.
SpillwaveSolutions/okf-time-series
- Latest recorded source activity
- SkillsMP catalog refreshed
- skills collected
- 12
- GitHub stars
- 0
- GitHub forks
- 1
Install with an AI assistant
Copy this prompt into the AI assistant you're using.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/SpillwaveSolutions/okf-time-series.Loading the repository README…
Skills in this repository
Showing 12 of 12 collected skills.
Copy a host JSONL transcript into an immutable sessions/<slug>.source.jsonl snapshot. No LLM.
Scheduled hourly tick. Writes an Hour node only when the window has closed segments and no open ones. Sparse.
Commit a temporal node. The model proposes body text; this script writes frontmatter.
Drop telemetry files older than 90 days. Pruning is a git commit of the working tree.
Walk Year → Month → Week → Day → Hour → Session using only the filesystem.
Close sessions open longer than the global watchdog (default one hour). Per-role is phase two.
Load okf-time-series via LangChain Deep Agents SkillsMiddleware / skills=.
Bind a Grok Bot agent to okf-time-series. Isolation, identity, deterministic writes.
Scaffold okf/temporal under SECOND_BRAIN_ROOT.
Source text: Undetermined
Open/close an isolated write session. Uses second-brain-core brain_session.py; does not fork the protocol.
Validate temporal nodes: type, period, aggregates, session identity.