pickup

pickup is a skill for Claude Code, Codex from kaisa-kucherenko/claude-code-flow. It costs 106 tokens per session (555 once invoked), scanned A, original, MIT.

A workflow for continuing work from a handoff file, which records what a previous session completed and what should happen next. It checks that the recorded project state still matches reality before continuing.

In plain words
What is it for?
Use it with /pickup or a handoff request to find the relevant HANDOFF file, verify its branch and files, run listed checks, and continue the next task.
Why use it?
It reduces the risk of blindly following stale instructions after the codebase or Git history has changed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it with /pickup or a handoff request to find the relevant HANDOFF file, verify its branch and files, run listed checks, and continue the next task.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kaisa-kucherenko/claude-code-flow/pickup
Install

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.

Any agent
npx skills add kaisa-kucherenko/claude-code-flow --skill pickup
Clone the repo
git clone --depth 1 https://github.com/kaisa-kucherenko/claude-code-flow

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for pickup

README.md
[![agentmods](https://agentmods.dev/badge/skills/kaisa-kucherenko/claude-code-flow/pickup.svg)](https://agentmods.dev/skills/kaisa-kucherenko/claude-code-flow/pickup)
Your own site
<a href="https://agentmods.dev/skills/kaisa-kucherenko/claude-code-flow/pickup"><img src="https://agentmods.dev/badge/skills/kaisa-kucherenko/claude-code-flow/pickup.svg" alt="Measured on agentmods" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 555 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00106 $0.00555
Opus 5 $0.00053 $0.00278
Sonnet 5 $0.00021 $0.00111
Haiku 4.5 $0.00011 $0.00056

Measured 7d ago against content hash 84dc27c3ecfc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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 7d 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.

skills/pickup/SKILL.md · 49 lines

What it actually says

Pickup — continue from a handoff

Find the file

  • /pickup <slug|issue|topic> — match against handoff filenames.
  • /pickup bare: glob the project root for HANDOFF_*.md.
    • Exactly one → proceed.
    • Several → show a compact list: filename, header topic, last-updated date, first line of its NEXT section — ask which to pick up.
    • None → say so; don't invent a handoff.
  • An @-mention that failed to attach (typo like HENDOFF) is still a pickup request — glob and read the file yourself.

Verify before acting — never execute a handoff blindly

The file records conclusions as of its write time; ground truth may have moved. Before starting:

  1. Compare its recorded branch/HEAD/commit hashes against git log — flag commits that appeared since, or a recorded HEAD that is gone.
  2. Spot-check that key files/artifacts it names still exist.
  3. If it lists verification commands with checkpoints, run the cheap ones.

Report in a few lines: the task, what the handoff says is next, and any divergences found. Material divergence (the plan's premise no longer holds) → surface it and ask before proceeding. Cosmetic drift → note it and continue.

Work rules

  • Start with the NEXT section — or the user's explicit steer in the same message ("do step 4") which overrides it.
  • "Ruled out — do not reopen" is a hard constraint: do not re-litigate ruled-out hypotheses unless new evidence contradicts the recorded reason.
  • Open questions in the file are the user's to answer — ask when one blocks the work.
  • Need detail the file lacks? The header's session id allows claude --resume <id> in another terminal; prefer asking the user before archaeology.
  • From here on this file is the live handoff of THIS session — /handoff updates it (and marks stages done) as work progresses.
Changes

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.

  1. 7d ago First seen · 49 lines · 106 tokens per session scan A 84dc27c3ecfc

Subscribe to this mod's changes

pickup is a skill published in the GitHub repository kaisa-kucherenko/claude-code-flow (19 stars, last pushed 11d ago), licensed MIT. It adds 106 tokens to every session and 555 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

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…

openai/codex · 114 tokens