recap — Claude Code skill: roll up recent agent sessions
Summarizes the last N agent sessions for the current project, grouped by date, with highlight observations per session. Useful when you want a rollup of recent work.
npx skills add rohitg00/agentmemory --skill recap -a claude-codeWhat recap does
The skill takes an argument like last N, today or this week. Leave it empty and you get the last 10 sessions. It calls memory_sessions with the project identifier and a limit, follows nextCursor until the requested window is covered, then sorts by startedAt descending.
Sessions are grouped by local calendar date as YYYY-MM-DD. Each line shows the first 8 characters of the id, the title or first prompt, the observation count and the status. Highlights come from memory_recall, called with the same project and agentId, and every result is checked against its session before it lands in the output. The run ends with a totals line: sessions, days, observations.
Only what the memory tools returned gets summarized. An empty window is a real answer, not a reason to invent activity. If memory_sessions or memory_recall is unavailable, the skill points you at TROUBLESHOOTING.md. It ships alongside handoff, session-history and recall — same session data, different lens.
What it helps with
- recall what you worked on in this project over the past week
- list agent sessions with dates and statuses
- pull highlight observations per session instead of paraphrasing from memory
- get an honest answer when the window has no sessions at all
- produce a totals line for sessions, days and observations
Example prompts for the agent
- Give me a recap for today in this project
- Recap this week
- Recap the last 20 sessions
How to install recap
1Skills CLI (Vercel)
npx skills add rohitg00/agentmemory --skill recap -a claude-code2Manually: put the files in place
~/.claude/skills/recap/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/recap/
1Skills CLI (Vercel)
npx skills add rohitg00/agentmemory --skill recap -a codex2Manually: put the files in place
.agents/skills/recap/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add rohitg00/agentmemory --skill recap -a cursor2Manually: put the files in place
.cursor/skills/recap/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install rohitg00/agentmemory recap2Manually: put the files in place
.github/skills/recap/SKILL.md1Skills CLI (Vercel)
npx skills add rohitg00/agentmemory --skill recap -a gemini-cli2Platform CLI
gemini skills install https://github.com/rohitg00/agentmemory --path plugin/skills/recapManually: put the files in place
.devin/skills/recap/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add rohitg00/agentmemory --skill recap -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about recap
How do I install recap in Claude Code?
Run npx skills add rohitg00/agentmemory --skill recap -a claude-code. The skill file lands at ~/.claude/skills/recap/SKILL.md.
What does recap do?
It summarizes the last N agent sessions for the current project, groups them by date and adds highlight observations for each session.
What does recap need to work?
Access to the memory_sessions and memory_recall tools. Without them the skill points you to TROUBLESHOOTING.md.
Source text
SKILL.md · Apache-2.0
---
name: recap
description: 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.
argument-hint: "[last N | today | this week]"
user-invocable: true
---
The user wants a recap. Time window args: $ARGUMENTS
## Quick start
```json
memory_sessions { "project": "<current-project-id>", "limit": 30 }
```
Then per surviving session: `memory_recall { "query": "<top concepts>", "project": "<current-project-id>", "limit": 3 }`.
When an agent is requested, pass the same `agentId` to both calls.
Expected output:
```text
2026-06-07
7f3a9c2 · "Auth refresh rework" · 14 obs · completed
- [8] Rotate refresh tokens on every use
3 sessions across 2 days, 41 observations.
```
## Why
Only summarize sessions and observations the tools returned. An empty window is
a real answer, not a prompt to invent activity.
## Workflow
1. Parse `$ARGUMENTS`: `today` = current local date; `this week` = last 7 days;
`last <n>` or bare numeric = most recent N; empty = `last 10`.
2. Call `memory_sessions` with the exact recorded project identifier when known
and the requested `agentId`. Follow `nextCursor` with the same filters until
the requested window is covered or pages end. When the project identifier is
unknown, match normalized `cwd` by directory boundary across pages before
applying the time/count window. Sort by `startedAt` descending.
3. Group survivors by local calendar date (YYYY-MM-DD).
4. Per session list id (first 8), title or first prompt, observation count,
status. Obtain highlights with `memory_recall`, retaining project/agent scope,
and verify each result belongs to that session before including it.
5. End with "N sessions across M days, K observations."
## Anti-patterns
WRONG: window is empty, so you summarize "a productive week of auth work" from
memory of the conversation.
RIGHT: "No sessions in the last 7 days for this project."
## Checklist
- Window parsed correctly from the argument.
- Sessions filtered to the current project's cwd.
- Highlights come from `memory_recall`, not paraphrase.
- Totals line reflects the actual counts shown.
## See also
- `handoff`, `session-history`, `recall`: same session data, different lens.
## Troubleshooting
See [TROUBLESHOOTING.md](TROUBLESHOOTING.md) if `memory_sessions` or `memory_recall` is not available.
© rohitg00 · Apache-2.0 · rohitg00/agentmemory