Borrowing it
Nothing to install: this file belongs to 0xSoftBoi/suwappubot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/0xSoftBoi/suwappubot/main/.claude/skills/handoff/SKILL.mdgit clone --depth 1 https://github.com/0xSoftBoi/suwappubotWrote 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/0xsoftboi/suwappubot/handoff)<a href="https://agentmods.dev/skills/0xsoftboi/suwappubot/handoff"><img src="https://agentmods.dev/badge/skills/0xsoftboi/suwappubot/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.
<a href="https://agentmods.dev/skills/0xsoftboi/suwappubot/handoff"><img src="https://agentmods.dev/badge/skills/0xsoftboi/suwappubot/handoff.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 | $0.00057 | $0.00473 |
| Opus 5.5 | $0.00023 | $0.00189 |
| Sonnet 5.5 | $0.00011 | $0.00095 |
| Haiku 4.5 | $0.00006 | $0.00047 |
Grade A, and why
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 1mo 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.
What it actually says
/handoff — checkpoint, then clear
Long sessions are the single largest source of token spend: every turn re-sends the entire conversation. A 1,000-turn session pays for its own history 1,000 times. This skill makes clearing cheap by writing down the only part worth keeping.
Do this
-
Write
.claude/handoff.md(overwrite it) with only what a fresh session could not re-derive in one command. Keep it under 40 lines.# Handoff — <YYYY-MM-DD> — <task in one line> ## State <done / in-progress / blocked, one line> ## Files touched - path:line — what changed and why ## Decisions made (and why) - <the reasoning a fresh session would otherwise redo> ## Next step 1. <the single next concrete action> ## Dead ends — do NOT retry - <approach tried, why it failed> -
Do not include: file contents, command output, the repo layout, anything already in
CLAUDE.md, or narration of what happened. A fresh session getsCLAUDE.mdandgit difffor free — don't pay to restate them. -
Reply with the path and a 3-bullet summary, then tell the user to
/clear.
Resuming
A new session starts with: Read .claude/handoff.md, then git status && git diff --stat.
That is the whole warm-up. If the handoff needed more than that, it was written wrong.
Rules
.claude/handoff.mdis a scratch file, one task at a time — overwrite, never append.- If the task is genuinely finished and merged, write "State: done, nothing pending" and say so; don't manufacture next steps.
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.
- 1mo ago First seen · 52 lines · 57 tokens per session scan A 1f980e5af0e3
handoff is a skill published in the GitHub repository 0xSoftBoi/suwappubot (4 stars, last pushed 4d ago), licensed Apache-2.0. It adds 57 tokens to every session and 473 once invoked, about $0.0002 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 2026-09-27.
Other skills, from other repositories
sessions
Session management, conversation history, and checkpoints.
auto-reply
Automatic response rules, patterns, and scheduled messages.
memory
Persistent memory system for preferences, facts, and notes.
presence
Online status, activity tracking, and multi-device sync.
processes
Background jobs, long-running processes, and task management.
qmd
Local hybrid search for markdown notes and docs. Use when searching notes, finding related content, or retrieving documents from indexed collections.