Install
$ agentstack add skill-noluyorabi-claude-code-recap-recap ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
recap: re-entry radar for Claude Code sessions
One command, full overview of recent sessions across every project on this machine. Built for the post-reboot moment: which projects, what was each session about, and the exact command to jump back in.
How to run it
Personal or project install (the skill directory is on disk next to this file):
python3 ~/.claude/skills/recap/recap.py [flags]
Plugin install (Claude Code exports the plugin root):
python3 "$CLAUDE_PLUGIN_ROOT/skills/recap/recap.py" [flags]
Nothing to install beyond Python 3 (stdlib only, no third-party packages).
| Flag | Meaning | |------|---------| | (none) | last 15 sessions, newest first, instant, no network | | --since 7d | only sessions active in the window (30m, 24h, 7d, 2w) | | --project foo | filter by substring of the absolute project path | | --limit N | max rows (default 15) | | --json | machine-readable output with full session ids and resume commands | | --smart | real one-sentence summaries via ONE claude -p haiku call (network, ~10s) | | --pick | choose a row interactively, then cd + claude -r into it directly | | --open | open EVERY listed session in its own new terminal tab and resume it there (macOS) | | --claude-flags "..." | extra flags for each resumed claude (e.g. "--chrome --dangerously-skip-permissions"); also shown in the printed resume lines and --json | | --terminal auto\|iTerm2\|Terminal | which app --open drives (default: iTerm2 when installed) | | --yes / -y | skip the --open confirmation prompt (required when stdin is not a TTY) | | --dry-run | with --open: print the tabs and commands, open nothing | | --color | force ANSI colors when output is piped (e.g. inside Claude Code) | | --plain | no ANSI at all (also honors NOCOLOR / FORCECOLOR env) |
Usage examples
# after a reboot: what was I doing?
python3 ~/.claude/skills/recap/recap.py
# everything in one repo this week
python3 ~/.claude/skills/recap/recap.py --since 7d --project my-repo
# jump straight back into a session
python3 ~/.claude/skills/recap/recap.py --pick
# re-open yesterday's whole working set in terminal tabs, browser enabled, no permission prompts
python3 ~/.claude/skills/recap/recap.py --since 24h --limit 12 \
--open --yes --claude-flags "--chrome --dangerously-skip-permissions"
# preview first, open nothing
python3 ~/.claude/skills/recap/recap.py --open --dry-run
# feed into other tooling
python3 ~/.claude/skills/recap/recap.py --json --limit 50
The --open flag
Restores a whole working set at once. It opens one new tab per listed session and types the resume command into it. Rules:
- The session recap itself runs in is skipped automatically (matched on
CLAUDE_CODE_SESSION_ID), so it never re-opens itself. - Sessions whose project directory no longer exists are skipped and reported, never opened.
- Scope comes from the normal filters, so
--limit/--since/--projectdecide exactly which tabs appear. Check with--dry-runbefore committing. - Without
--yesit asks for confirmation; with piped stdin (Claude Code's Bash tool) it refuses to open unless--yesis passed. --claude-flagsis passed through verbatim to every tab.--dangerously-skip-permissionsdisables all permission checks in each opened session; the script prints a warning before doing it.- Tab opening drives iTerm2 or Terminal through
osascript, so it is macOS-only. On other platforms--openexits with a clear message;--open --dry-runstill prints the commands so they can be pasted anywhere.
When Claude runs this skill
Run the script with Bash, ALWAYS with --color (tool output is piped, auto-detection would strip the colors; Claude Code renders ANSI). Add --since/--project if the user narrowed the question, then relay the table. Quote the resume command (cd && claude -r ) for any session the user wants to re-enter. Only add --smart if the user explicitly asks for better summaries; it makes a network call.
Use --open only when the user explicitly asks to re-open or resume the sessions. Because the Bash tool pipes stdin, --open needs --yes; treat the user's request as the confirmation, and set the scope with --limit/--since so no unwanted session gets a tab. Pass --claude-flags only with flags the user named; state the permission-bypass warning in your reply whenever --dangerously-skip-permissions is among them.
Data sources and guarantees
~/.claude/history.jsonlis the fast index (prompt text, timestamp, project path, session id).CLAUDE_CONFIG_DIRis honored when set.~/.claude/projects//.jsonltranscripts are parsed only for the displayed rows (title, branch, model, turn count). Project paths always come from thecwd/projectfields, never decoded from folder names (that encoding is lossy).- Summary preference: Claude Code's own
ai-titleline, else the first real user prompt, else(no prompt). --smartprivacy: the only path that leaves the machine. It shells out to the localclaudeCLI once and sends, for the listed sessions only, each session's 8-character id prefix, its title (first 150 characters), and its first user prompt (first 300 characters). No file bodies, no transcript contents, no other sessions. Ifclaudeis not on PATH,--smartis skipped with a warning and the offline summaries are used.- Turn count groups assistant streaming chunks by message id and is labeled approximate.
- Broken or partial JSONL lines are skipped, never fatal. Times shown in the local timezone.
- Display: day-grouped timeline (Today green, Yesterday amber), 14-day activity sparkline in the header, per-project colored dot (stable hash), four-level gray hierarchy with one accent color, per-session resume line indented with spaces only (safe to copy). Falls back to plain text when piped or when NO_COLOR is set.
- Read-only: the tool never writes or deletes anything. It sees only sessions still on disk (Claude Code prunes old ones).
--openand--pickare the only side-effecting paths:--opendrives iTerm2/Terminal viaosascript,--pickexecsclaude -rin the chosen directory. Neither writes or touches session data.
Optional shell alias
alias recap='python3 ~/.claude/skills/recap/recap.py'
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: noluyorAbi
- Source: noluyorAbi/claude-code-recap
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.