
Recap
When you've been away from a project or just lost track of what Claude worked on yesterday, this pulls your last N agent sessions and groups them by date with the most important observations surfaced per session. It parses "today", "this week", or "last 10" from your query, filters to the current project directory, and uses memory_recall to grab highlights rated 7 or above. The output is compact: session ID prefix, title, observation count, and a few indented bullets. The anti-pattern section is worth reading because it explicitly refuses to hallucinate productivity when the time window is empty, which is the right call but not what every summarizer does.
- skills.sh installs
- 14.3K
- GitHub stars
- 30.2K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add rohitg00/agentmemory --skill recap --agent claude-codeInstalls into .claude/skills of the current project.
Files
The user wants a recap. Time window args: $ARGUMENTS
Quick start
memory_sessions { "project": "<current-project-id>", "limit": 30 }
Then per surviving session: memory_recall { "query": "<top concepts>", "project": "<current-project-id>", "limit": 3 }.
When an agent is requested, pass the same agentId to both calls.
Expected output:
2026-06-07
7f3a9c2 · "Auth refresh rework" · 14 obs · completed
- [8] Rotate refresh tokens on every use
3 sessions across 2 days, 41 observations.
Why
Only summarize sessions and observations the tools returned. An empty window is a real answer, not a prompt to invent activity.
Workflow
Sponsors
Details
- Repository
- github.com/rohitg00/agentmemory
- Category
- AI & Agent Building
- First seen
- Jul 14, 2026