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.
npx agentmods add skills/baleen37/bstack/pickupnpx skills add baleen37/bstack --skill pickupgit clone --depth 1 https://github.com/baleen37/bstackWhat 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 | $0.00069 | $0.01821 |
| Opus 5 | $0.00034 | $0.00911 |
| Sonnet 5 | $0.00014 | $0.00364 |
| Haiku 4.5 | $0.00007 | $0.00182 |
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 yesterday.
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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pickup: Resume from a handoff file
Read a handoff written by /handoff and continue the previous session's work. Pair with /handoff.
The hard part is not finding the directory — Claude can do that. The hard part is not silently picking the wrong file, not summarizing the Resume Prompt away, and not papering over a worktree/branch mismatch with inference. This skill exists to enforce that discipline.
What /pickup does
- Lists candidates from
~/.claude/handoff/ - If multiple candidates exist, asks the user to pick (never auto-matches by topic/branch)
- Reads the chosen file
- Compares its
worktreeandbranchto the current ones, reports any mismatch, and stops to ask before proceeding when they differ - Quotes the Resume Prompt verbatim in a code block — never paraphrased
- Surfaces Failed Approaches and Open Questions
- Cross-checks the handoff against
git logsince the handoff was written, and reports any work that may already be done - Then continues using the recovered context
What /pickup does NOT do
- Does not write or modify files
- Does not auto-checkout branches or change worktrees
- Does not pick a file by topic match, branch name, or recency alone when multiple files exist
- Does not summarize, paraphrase, or "improve" the Resume Prompt
- Does not search project-local directories — only
~/.claude/handoff/ - Does not silently skip Failed Approaches even when they look outdated
Steps
-
List candidates (newest first):
ls -t ~/.claude/handoff/*.md 2>/dev/null | head -10If empty/missing → tell the user there is nothing to pick up. Stop. Do not fabricate context from
git log. -
Choose a file — strict rules:
- 0 candidates → stop (above).
- 1 candidate → use it.
- 2+ candidates → use AskUserQuestion (load via ToolSearch if it's a deferred tool:
ToolSearch select:AskUserQuestion; if unavailable, ask inline). Show top 5 with<filename> — <first-line title>. Never auto-pick by branch name match, topic match, or "most recent." The user picks. - If the user's request named a topic, you may suggest a default in the question, but the user still confirms.
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.
- yesterday First seen · 133 lines · 69 tokens per session scan A ffc5f947d42d
pickup is a skill published in the GitHub repository baleen37/bstack (4 stars, last pushed 12d ago), licensed MIT. It adds 69 tokens to every session and 1,821 once invoked, about $0.0003 per session on Opus 5. 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…