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 skills add juxt/claude-plugins --skill pick-upgit clone --depth 1 https://github.com/juxt/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/skills/juxt/claude-plugins/pick-up)<a href="https://agentmods.dev/skills/juxt/claude-plugins/pick-up"><img src="https://agentmods.dev/badge/skills/juxt/claude-plugins/pick-up/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/skills/juxt/claude-plugins/pick-up"><img src="https://agentmods.dev/badge/skills/juxt/claude-plugins/pick-up.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 | $0.00072 | $0.01109 |
| Opus 5.5 | $0.00029 | $0.00444 |
| Sonnet 5.5 | $0.00014 | $0.00222 |
| Haiku 4.5 | $0.00007 | $0.00111 |
Grade A, and why
pick-up 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 3d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pick-up
Interpret MUST, MUST NOT, SHOULD, SHOULD NOT, MAY, etc. per RFC 2119.
Success: the session works from the issue alone, nothing in its neighbourhood that changes the picture has gone unreported, and every commit and PR the session drafts finds its reasoning already written in the plan.
Before you start
- Load
chalk:issue, which loadschalk:voice. - Ground it in the repo, not the transcript: the branch,
git logand linked PRs say what has landed.
1. Read the issue and its neighbourhood
The issue, its parent, its sub-issues, what blocks it and what it blocks, and its linked PRs.
2. Report what the scan found
Say what the neighbourhood tells you about this issue being worked now, and carry on.
The why now, where there is one, is the issue's own (chalk:issue); an issue without one is opportunistic.
-
Where the scan changes the picture, wait for the user's agreement before changing anything, the tracker included. An open blocker, a duplicate, or a card that supersedes this one.
-
Where the user named an umbrella rather than a piece of it, ask which piece. You MUST NOT pick the most plausible-looking sub-task instead.
3. Report and resolve gaps in the issue
Against chalk:issue's palette: a missing goal, unclear scope, open questions nobody has answered.
Report them and resolve them; the answers reach the issue through chalk:issue.
4. Sort the metadata
Assignee, status, board — whatever the project's tracker conventions say for a card being picked up. Where they don't say, ask.
5. Start the plan
The session's plan — Claude Code's plan file, or the host's equivalent — unless the project names another place. Only the session writes it.
- It opens with one line:
Journalled per chalk:pick-up — <issue link>, so a session after a compaction knows which skill to reload. - It links the issue rather than copying it.
- It holds what has to land, and below it, apart, the journal.
- What has to land, not which files to touch.
- What has to land SHOULD be a goal tree (
chalk:goal-tree): the issue's goal at the root, what lands at the leaves. Test each node for sufficiency, markcheck:where unsure, and say where sufficiency leans on what the user already knows about the system. - A sub-goal names what it depends on. It's ready once everything it depends on is done and no open question blocks it.
- What's in hand sits at the top: the sub-goal being worked, and anything that interrupted it, innermost first.
- When a sub-goal's commit is made, mark it done with the commit's subject, not its SHA, which a rebase rewrites.
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.
- 3d ago Changed 49a5f8f6a697
- 4d ago Changed · +4 lines · -1 tokens per session bfd59d4cae18
- 11d ago First seen · 78 lines · 73 tokens per session scan A c5fbeef4640f
pick-up is a skill published in the GitHub repository juxt/claude-plugins (10 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 1,109 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-06.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…