temporalthread
Skill1 starsChanged 4 months agoMITView on GitHub
Retrieve durable temporal context and maintain evidence-based follow-up commitments across Claude Code sessions.
In this repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- temporal-awarenessSkill
- temporalthreadSkill
- temporalthreadSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Keep context compact and do not request raw history unless explicitly needed and privacy-permitted.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
TemporalThread
- Retrieve
get_temporal_contextat session start/resume, after a meaningful gap, or when the user refers to yesterday, tomorrow, later, last time, next week, or elapsed time. - Resolve historical relative phrases from their original timestamp and timezone, never from the current date.
- Record a commitment only for an explicit future follow-up. Preserve uncertainty instead of inventing a deadline.
- Mark a commitment completed or cancelled only when there is evidence. Silence is not completion.
- Mention elapsed time only when it helps answer the user.
- Keep context compact and do not request raw history unless explicitly needed and privacy-permitted.
Hooks are a best-effort capture aid. Use record_interaction manually when a relevant event was not captured.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.