reboot

reboot is a skill for Claude Code from ao92265/claude-code-playbook. It costs 117 tokens per session (515 once invoked), scanned A, original, MIT.

A session-handoff tool that turns the current task and its progress into a short prompt for a fresh coding-agent session.

In plain words
What is it for?
Use it to prepare a clean reprompt when restarting a session, clearing context, or moving ongoing work to a new terminal.
Why use it?
It helps recover when a conversation becomes too long or stale without losing the goal, decisions, files, or next step.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the playbook plugin — 49 skills, 4 hooks 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/ao92265/claude-code-playbook/reboot
Any agent
npx skills add ao92265/claude-code-playbook --skill reboot
Clone the repo
git clone --depth 1 https://github.com/ao92265/claude-code-playbook

Made for: Claude Code.

Or install playbook, the plugin that ships this one along with the rest of its 49 skills, 4 hooks.

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 reboot

README.md
[![agentmods](https://agentmods.dev/badge/skills/ao92265/claude-code-playbook/reboot.svg)](https://agentmods.dev/skills/ao92265/claude-code-playbook/reboot)
Your own site
<a href="https://agentmods.dev/skills/ao92265/claude-code-playbook/reboot"><img src="https://agentmods.dev/badge/skills/ao92265/claude-code-playbook/reboot.svg" alt="Measured on agentmods" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 515 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 $0.00117 $0.00515
Opus 5 $0.00059 $0.00258
Sonnet 5 $0.00023 $0.00103
Haiku 4.5 $0.00012 $0.00052

Measured 6d ago against content hash 7bd0cf6f53c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

reboot 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.

skills/reboot/SKILL.md · 38 lines

What it actually says

reboot

The session is old or bloated and should be cleared. Your job: hand the user a clean, self-contained prompt they can paste into a fresh session and keep going — no thread lost.

You can't run /clear yourself. You produce the reprompt; the user clears and pastes.

Sources

  • Primary: the current conversation you already hold. That's the real source of the goal and state.
  • Cross-check / fill gaps: the freshest handoff in ~/.claude/handoffs/ — pick the one matching the current working directory, else the most recently modified — and its .compact.md sibling if present. These are the same sources sessionstart-handoff.sh re-injects into a new session.

Distill into the reprompt

Capture only what a fresh Claude needs:

  • Goal — what "done" looks like, in one or two lines.
  • State — what's already done / decided.
  • Next step — the immediate thing to do.
  • Constraints — hard rules or decisions already locked in.
  • Key paths — files/dirs in play.

Drop dead-ends, resolved tangents, and tool noise.

Output

Two short lines first: why the session looks stale, and what to do — /clear (or open a new terminal), then paste the block below.

Then one fenced code block = the paste-ready reprompt. Write it as a direct instruction to a fresh Claude. It must be fully self-contained — assume the reader saw none of this session. No "as discussed", no dangling pronouns.

Honesty

Don't invent state. If branch, dirty files, or anything else is uncertain, write "verify before acting" instead of asserting it — same disclaimer the handoff itself uses. A wrong "current state" is worse than an admitted gap.

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 · 38 lines · 117 tokens per session scan A 7bd0cf6f53c5

Subscribe to this mod's changes

reboot is a skill published in the GitHub repository ao92265/claude-code-playbook (10 stars, last pushed 19d ago), licensed MIT. It adds 117 tokens to every session and 515 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

agent-memory

../../../engineering/agent-memory/skills/agent-memory/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens