recap Skill (agentmemory) for Claude Code: Session Rollup

Summarizes your recent agent sessions for the current project, grouped by day, for anyone who asks what they have been working on.

Installs: 14K; on skills.sh
Stars: 30.1K; on GitHub
Files: 2; besides SKILL.md
Updated: Oct 2026; last repo commit

/recap lists your last agent sessions for the current project, grouped by date. Each session shows its short ID, title, number of observations and status, with a few highlight lines pulled from agentmemory. It ends with a totals line such as "N sessions across M days, K observations."

You pick the window with an argument: last N, today or this week. With no argument it shows the last 10. It only reports what the memory tools return, and an empty window gets a plain "no sessions" answer.

Good for

Developers who start the day wanting a rollup of yesterday’s agent sessions
Anyone running agentmemory across several projects or agents
People writing a weekly update from agent work

Install recap

Claude Code

Copy this prompt.

Install the recap skill in Claude Code. Run this command:

npx -y @agentmemory/agentmemory@latest

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js 20 or newer.

This skill only works when the memory server is running and the agentmemory MCP tools are connected. The plugin route is the one the README recommends for Claude Code. The skills-only route installs all 17 skills but does not connect the MCP tools by itself. Pick one route, not both.

From the project README. Source.

What's in the skill

When it loads

Summarize the last N agent sessions for the current project, grouped by date, with highlight observations per session. Use when the user asks "recap", "what have we been doing", "today", "this week", or wants a rollup of recent work.

Sections in SKILL.md

Quick start
Why
Workflow
Anti-patterns
Checklist
See also
Troubleshooting

Key facts

Author: rohitg00
Repository: rohitg00/agentmemory
Installs on skills.sh: 14,047 as of 2026-11-02
GitHub stars: 30,069 for the whole rohitg00/agentmemory repo
License: Apache-2.0 (repo and plugin.json)
Last repo commit: 2026-10-29
What is inside: 3 files including SKILL.md: EXAMPLES.md and TROUBLESHOOTING.md. It bundles no scripts.
skills.sh audits: Gen Agent Trust Hub: fail; Socket: pass; Snyk: pass
Part of: The agentmemory plugin (17 skills, 12 hooks, 54 MCP tools per plugin.json)
Needs: The agentmemory server running, with its memory_sessions and memory_recall tools connected
Usage: /recap with last N, today or this week

What it includes

today, this week, last N, or the last 10
today means the current local date, this week means the last 7 days, last N or a bare number means the N most recent sessions, and an empty argument means the last 10.
Try: “/recap this week”
Parse the window
Lists sessions for the project, following pages
Called with the project identifier, a limit and an optional agent ID. It follows nextCursor until the window is covered, then sorts by start time, newest first.
Network · memory_sessions
One block per calendar day
Sessions are grouped by local date in YYYY-MM-DD form.
Group by date
Pulls highlights for each session
Called per session with its top concepts, keeping the project and agent scope, and each result is checked to belong to that session before it is shown.
Network · memory_recall
Sessions, days and observations counted from the results
The last line must match the counts actually shown.
Totals line

From the official docs

Permissions

Medium risk

The skill reads your stored session history, which the agentmemory plugin records through hooks. Review what the plugin captures before you rely on it.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

The plugin records your sessions through hooks
The README lists captured data: user prompts (privacy-filtered), tool name, input and output, errors, and the assistant reply of each turn. Review what is stored in the viewer, and use the forget skill to remove entries. github.com
Installing starts a local server and runs npm code
The setup command pulls the latest package with npx and starts a background server. On macOS and Linux it also needs curl, sh and tar for automatic runtime setup. github.com
Saved memories flow back into later sessions
plugin.json says the plugin injects context into future sessions, and the README says automatic injection through the shared hooks is opt-in. Recalled text is read by the assistant, so avoid saving text you do not trust. github.com

Security advisories

No published security advisories as of Nov 2, 2026.

Technical details

Turning on read-only	No read-only switch is documented for these skills.
Talks to	The server and viewer bind to loopback (127.0.0.1) by default. Compression or embeddings with a provider you configure use that provider. Local semantic search downloads an embedding model on first use if you set EMBEDDING_PROVIDER=local
Sign-in and keys	A local server creates a random secret at ~/.agentmemory/secret with mode 0600 and the bundled clients read it. A remote server needs AGENTMEMORY_SECRET in your environment.
Data retention	Memories are stored on your machine in the agentmemory data folder until you delete them. The README says API keys, bearer tokens and <private> tags are stripped before storage.
Scopes	Reads session lists and recalled observations from the agentmemory server The Claude Code plugin registers 12 hooks that run node scripts on events such as every prompt, every tool call and the end of each turn The plugin ships a .mcp.json that starts a node bridge to the local memory server Setup runs npx -y @agentmemory/agentmemory@latest, writes config to ~/.agentmemory and starts a server on localhost:3111

Questions

What does /recap do?

It summarizes your last agent sessions for the current project, grouped by date, with highlights from agentmemory. You can ask for today, this week or the last N sessions.

How do I install it?

Use the install box above. The skill needs a running agentmemory server and its MCP tools. The box lists the server step first and the plugin route the README recommends for Claude Code.

Does it work without agentmemory?

No. It gets its data from the memory_sessions and memory_recall tools. If they are missing, its TROUBLESHOOTING.md walks through reconnecting the MCP connection.

What happens if there were no sessions?

It says so, for example "No sessions in the last 7 days for this project." SKILL.md tells it not to invent a summary from the conversation.

How is it different from session-history, handoff or recall?

SKILL.md lists handoff, session-history and recall as the same session data through a different lens. Recap is the dated rollup. Use recall to search the observations inside one session.

Is it safe?

The skill bundles no scripts and calls two memory tools to read sessions. The agentmemory plugin around it does more: it installs hooks that record your prompts and tool calls, and runs a local server. See the permissions section for those.

Information

updated Nov 2, 2026

Repository: rohitg00/agentmemory
Folder: plugin/skills/recap

rohitg00/agentmemory skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 8

rohitg00/agentmemory README · github.com
skills CLI commands · github.com
recap SKILL.md · github.com
recap TROUBLESHOOTING.md · github.com
plugin hooks.json · github.com
plugin .mcp.json · github.com
plugin.json · github.com
Shared TROUBLESHOOTING.md · github.com