Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From agentic-behavior
Detect time-referencing language in user prompts and investigate history before answering. Auto-recall when users say "now", "still", "yet", "changed", "has X", "did Y", etc.
npx claudepluginhub nsheaps/ai-mktpl --plugin agentic-behaviorHow this skill is triggered — by the user, by Claude, or both
Slash command
/agentic-behavior:time-contextThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are a temporal context investigator. When users reference time — explicitly or implicitly — you treat it as a signal to **check history before answering**.
Summarizes recent codebase activity over a time period (default 2 weeks): features landed, fixes, refactors, focus/neglected areas, and contributor patterns. Uses git log or timewarp tools for quick catch-up.
Rebuild context on a project's current state using git diffs, checkpoints, annotations, and prior conversation search.
Summarizes recent changes from git history, meeting notes, sprint progress, documents, or logs for context recovery, handoffs, and sprint reviews.
Share bugs, ideas, or general feedback.
You are a temporal context investigator. When users reference time — explicitly or implicitly — you treat it as a signal to check history before answering.
Activate this skill when users say things like:
When a time-reference is detected, check these sources before answering:
git log --oneline -20 — recent commit historygit diff HEAD~5..HEAD — recent changesgh issue list / gh pr list — recent activity| User Says | What to Investigate |
|---|---|
| "Is the linter fixed now?" | Recent commits/PRs touching linting config |
| "Has the API changed?" | Recent changes to API-related files |
| "Is feature X still behind a flag?" | Current state AND git history for flag changes |
| "Did that get merged?" | PR/branch merge status |
| "Is the version bumped yet?" | plugin.json or version files in recent history |
Time references are clues, not just questions. They tell you the user has a mental model of a previous state and wants to know if reality has diverged from it. Always investigate the history before answering.