passdown-pickup

passdown-pickup is a skill for Claude Code from vunm-io/passdown. It costs 55 tokens per session (748 once invoked), scanned A, original, MIT.

A startup guide for projects that keep handoff logs between coding sessions. It reads the latest handoff, checks it against the files, and summarizes what work should resume.

In plain words
What is it for?
Use it when starting or resuming work in a workspace with passdown logs, plans, and project instructions.
Why use it?
It helps a new session recover the actual project state without replaying a long conversation.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions AGENTS.md.

Part of the passdown plugin — 4 skills shipped together

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.

agentmods
npx agentmods add skills/vunm-io/passdown/passdown-pickup
Any agent
npx skills add vunm-io/passdown --skill passdown-pickup
Clone the repo
git clone --depth 1 https://github.com/vunm-io/passdown

Made for: Claude Code.

Or install passdown, the plugin that ships this one along with the rest of its 4 skills.

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 passdown-pickup

README.md
[![agentmods](https://agentmods.dev/badge/skills/vunm-io/passdown/passdown-pickup.svg)](https://agentmods.dev/skills/vunm-io/passdown/passdown-pickup)
Your own site
<a href="https://agentmods.dev/skills/vunm-io/passdown/passdown-pickup"><img src="https://agentmods.dev/badge/skills/vunm-io/passdown/passdown-pickup.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 748 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00055 $0.00748
Opus 5 $0.00028 $0.00374
Sonnet 5 $0.00011 $0.00150
Haiku 4.5 $0.00006 $0.00075

Measured 6d ago against content hash 01505ded7c47, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

passdown-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 6d 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.

plugins/passdown/skills/passdown-pickup/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Passdown Pickup

Start of shift: read the previous passdown before touching anything. The handoff wrote state into small files; pickup turns those files back into working context for a fraction of what replaying a transcript costs.

Configuration (read first)

Build the effective passdown configuration root-to-nearest. Read applicable AGENTS.md files from the workspace/repository root down to the current directory, plus any parent file explicitly referenced by a thin entrypoint. Merge ## passdown keys in that order: nearer values override the same key and inherit omitted keys. Resolve relative paths against the file that declared them.

The effective configuration should contain:

## passdown
- log_dir: <path for session logs>
- planning: markdown | openspec   # used to locate plan state
- plan_dir: <path for markdown plans>   # when planning: markdown

If log_dir is still missing, ask where session logs live and suggest adding it to the appropriate AGENTS.md.

Process

  1. Locate the handoff: list <log_dir> and sort by the filename's date and HHMMSS suffix, newest first. Read the newest log's frontmatter (status, branch, agent, plan); also read the frontmatter of any other recent logs, in case another agent worked in parallel. Frontmatter first, full text only for the logs that matter — that is what keeps pickup cheap.
  2. Read the passdown: for the relevant log(s), read Summary, Next steps, and especially Caveats / traps in full. Task state lives in the plan; session-scoped traps live nowhere but the log.
  3. Verify against reality — files may have moved on since the log was written:
    • the current branch vs the log's branch:;
    • git status and recent commits vs the log's "What was done";
    • each plan listed in plan: (a single path or a YAML list, resolved from the workspace root) — compare its checkboxes and any Dispatched: outcome lines against the log's next steps. Report any mismatch instead of silently reconciling it; the working tree and the plan win over the log.
  4. Brief, then wait: report status, verified next steps, and the traps. Pickup produces a briefing and a proposed first action — it never starts executing on its own. If the proposed work is a multi-task plan, the passdown-dispatch gate still applies before implementation.

Read the full file on GitHub · 68 lines

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. 6d ago First seen · 68 lines · 55 tokens per session scan A 01505ded7c47

Subscribe to this mod's changes

passdown-pickup is a skill published in the GitHub repository vunm-io/passdown (8 stars, last pushed 17d ago), licensed MIT. It adds 55 tokens to every session and 748 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.