pop-handoff

pop-handoff is a skill for Claude Code from aiya000/dotfiles. It costs 77 tokens per session (658 once invoked), scanned A, original, MIT.

A handoff retrieval procedure that reads the newest work note and then removes it from the shared memory repository. A handoff is a note left for the next coding session.

In plain words
What is it for?
Use it when starting work from a saved handoff and clearing that handoff afterward.
Why use it?
It prevents an old handoff from being offered again after a session has used it, while keeping its history available.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Good fit Use it when starting work from a saved handoff and clearing that handoff afterward.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aiya000/dotfiles/pop-handoff
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 aiya000/dotfiles --skill pop-handoff
Clone the repo
git clone --depth 1 https://github.com/aiya000/dotfiles

Made for: Claude Code.

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 pop-handoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/aiya000/dotfiles/pop-handoff/github.svg)](https://agentmods.dev/skills/aiya000/dotfiles/pop-handoff)
Your own site
<a href="https://agentmods.dev/skills/aiya000/dotfiles/pop-handoff"><img src="https://agentmods.dev/badge/skills/aiya000/dotfiles/pop-handoff/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.

agentmods 80×15 button for pop-handoff

Your own site · 80×15
<a href="https://agentmods.dev/skills/aiya000/dotfiles/pop-handoff"><img src="https://agentmods.dev/badge/skills/aiya000/dotfiles/pop-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 658 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 $0.00077 $0.00658
Opus 5.5 $0.00031 $0.00263
Sonnet 5.5 $0.00015 $0.00132
Haiku 4.5 $0.00008 $0.00066

Measured 10d ago against content hash 5cd3591888a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pop-handoff 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 10d 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.

.claude_global/skills/pop-handoff/SKILL.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pop-handoff

read-handoff is git stash apply: it reads the handoff and leaves it. This is git stash pop: the same reading, and then the handoff is gone -- from the repository, so neither the local machine nor a cloud session finds it again.

Handoffs are perishable. Once a session has picked one up, the next session should find the handoff that session writes, not this one again.

Steps

  1. Run the read-handoff skill, with this skill's argument if one was given, and do all of it: the issue overview, finding the handoff, following it to the memory file. Note which handoff file it picked up
  2. Remove that handoff, and only that one:
    • In ~/.ai-memory/handoff/: with the sync-memory skill, drop 'handoff: pop <file>' handoff/<file>.md handoff/<file>.declined. It is removed and pushed, with its decline-handoff-suggestion marker if it had one; the repository's history keeps it, so it can be brought back
    • In an old local place (~/tmp/claude-handoff/, ${TMPDIR:-/tmp}/claude-handoff/): not in the repository, so rm-dust <path> and its .declined marker, if any (rm in a cloud session, where there is no rm-dust)
  3. Run the sync-memory skill (sync) -- always, on your own, never left to the user. It pushes the removal if the drop could not
  4. Say in one line which file was removed, and whether the removal was pushed. Then carry on with what the handoff says to do first -- the pop is not the end of the job

When not to remove it

  • read-handoff fell back to another project's handoff (none for this one). AskUserQuestion first -- "Remove it" / "Leave it" -- since it was written for a different session
  • The handoff could not be followed -- the memory file it names is missing, or the user stopped partway. Leave it and say why, so it can be popped once it has actually been picked up
  • The memory file the handoff points at is never removed. It is the durable half, and other sessions still read it

Read the full file on GitHub · 42 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. 10d ago Changed · +2 lines 5cd3591888a3
  2. 17d ago Changed e9bbc82aa531
  3. 20d ago First seen · 40 lines · 77 tokens per session scan A d1d399073efd

Subscribe to this mod's changes

pop-handoff is a skill published in the GitHub repository aiya000/dotfiles (21 stars, last pushed 2d ago), licensed MIT. It adds 77 tokens to every session and 658 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 2026-09-26.