Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/cwakim/claude-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/cwakim/claude-plugins/pickup)<a href="https://agentmods.dev/commands/cwakim/claude-plugins/pickup"><img src="https://agentmods.dev/badge/commands/cwakim/claude-plugins/pickup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/cwakim/claude-plugins/pickup"><img src="https://agentmods.dev/badge/commands/cwakim/claude-plugins/pickup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01545 |
| Opus 5.5 | $0.00000 | $0.00618 |
| Sonnet 5.5 | $0.00000 | $0.00309 |
| Haiku 4.5 | $0.00000 | $0.00154 |
Grade A, and why
pickup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pickup
Read a handoff snapshot written by /handoff and continue the work (or the conversation) from it.
This is the other half of /handoff: a baton pass, not a session restore. It deliberately reads a distilled summary rather than replaying a transcript. (Named pickup, not resume, to avoid colliding with Claude Code's built-in /resume.)
Arguments ($ARGUMENTS)
- A path (anything containing
/or ending in.md) → read that file. Expand a leading~. - The word
list→ don't pick anything up; show what's in flight instead. Follow the List mode section below. - Any other text → treat it as a thread name: match it (case-insensitively, allowing partial matches) against the titles and goals in
~/.claude/handoff-index.md. One live match → pick that up. Several → show them and ask. None → say so and fall back to the discovery order below. - No argument → find the handoff via the discovery order below.
Discovery order (no argument given)
A handoff does not always live in the current repo: it may have been written from a sibling repo, the Desktop, or elsewhere. Walk this order and stop at the first hit:
.claude/handoff.mdin the current working directory.- The newest live entry in
~/.claude/handoff-index.md(the pointer index/handoffmaintains). Read the index and walk it top-down to the first path that still exists: entries can point at handoffs that were since deleted, so do not dead-end on a stale newest entry. Prune as you go: any entry whose path no longer exists is dead, so rewrite the index without those lines (keep the live ones in order) and tell the user which you removed. This keeps the index from accumulating pointers to deleted handoffs. - If neither resolves, say so and ask where the handoff lives.
If the resolved handoff lives outside the current working directory, say so explicitly and name its absolute path before acting on it, so a stale or wrong-repo pickup is obvious rather than silent.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 60 lines · 0 tokens per session scan A 780a4f42fc1c
pickup is a command published in the GitHub repository cwakim/claude-plugins (2 stars, last pushed 25d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,545 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
patterns
Scan recent sessions for recurring patterns and turn them into captures (rules, concept notes, writing seeds).
context-stats
Display context window usage and token statistics.
second-brain-mapping
Map your vault: extract structured metadata from every typed file, surface cross-doc insights, optionally build a knowledge graph.
cierre
A sales call just ended: turn its transcript into the full follow-up (CRM, tasks, email draft, reminder, coaching).
deconstruct
First-principles analyst: surface hidden assumptions, find foundational truths, rebuild from scratch.
diagnose
Run a self-check on your AI Brain Starter install (CLAUDE.md, Meta folder, skills, hooks, MCPs).