agentmods.dev

handoff-revive

handoff-revive is a skill for Claude Code from sofumel/claude-handoff-revive. It costs 208 tokens per session (5,616 once invoked), scanned C, original, MIT.

A handoff tool for saving a small checkpoint of ongoing work so it can be resumed in a fresh session without replaying the entire conversation.

In plain words
What is it for?
Use it to save or resume work checkpoints with the handoff-revive command.
Why use it?
It preserves the important goal, decisions, and lessons when a task needs to continue later.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the handoff-revive plugin — 1 skill, 11 commands, 5 hooks shipped together

not rated 6repo 2mo ago C scan 208 tokens original MIT

Good fit Use it to save or resume work checkpoints with the handoff-revive command.

Compare 6 skills from other repositories ↓
View source ↗ sofumel/claude-handoff-revive
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add sofumel/claude-handoff-revive
Claude Code
/plugin install handoff-revive

Made for: Claude Code.

Or install handoff-revive, the plugin that ships this one along with the rest of its 1 skill, 11 commands, 5 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 handoff-revive

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sofumel/claude-handoff-revive/handoff-revive"><img src="https://agentmods.dev/badge/skills/sofumel/claude-handoff-revive/handoff-revive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 208 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,616 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00208 $0.05616
Opus 5 $0.00104 $0.02808
Sonnet 5 $0.00042 $0.01123
Haiku 4.5 $0.00021 $0.00562

Measured 8d ago against content hash 0fc4f889ad7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

handoff-revive scanned grade C with 1 finding 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 8d ago.

The scan reads SKILL.md. This mod also ships 59 executable files (scripts/archive-current.ps1, scripts/archive-current.sh, scripts/check-freshness.ps1, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

No output = fresh, continue silently. If it prints warnings (file age / commits since save / branch mismatch / cannot verify), relay them to the user **in their language** at the top of your resume summary. Never refuse
plugins/handoff-revive/skills/handoff-revive/SKILL.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

handoff-revive

Save the minimum state needed to continue work later, so the next session can start fresh (NOT via --resume / -c) and reload only a small file.

Why not claude --resume

--resume and -c replay the entire prior transcript into context. For a typical session this costs tens of thousands of tokens (often 100k+ for long sessions) before the user even asks anything. A handoff file costs 1,000–3,000 tokens. Always prefer the handoff file when one exists.

Two modes

Mode 1: SAVE (/handoff-revive:save)

Triggered ONLY by:

  • User runs the slash command /handoff-revive:save
  • The UserPromptSubmit hook injects auto-save context (see Mode 1c below)

Do NOT trigger on natural-language phrases like "save handoff", "checkpoint", "ハンドオフ", "保存", "保存して中断". Users are expected to use the slash command. If a user types one of those phrases without the slash command, treat it as a regular message (gently remind them they can run /handoff-revive:save if they want to save).

Steps:

  1. Detect language — read .claude/handoff/lang if it exists. Trim whitespace; the file holds a language code (one of: ja, en, zh (Simplified), zh-TW (Traditional), ko, es, pt, de, fr, tr) with no trailing newline. Otherwise detect from the user's most recent message:

    • Hiragana/Katakana → ja
    • Hangul → ko
    • Han characters: simplified markers (e.g. 这, 国, 学) → zh; traditional markers (e.g. 這, 國, 學) → zh-TW
    • Cyrillic / Arabic → fall back to en
    • Latin script: detect by common diacritics + words:
      • é à è ç + words like fichier, avec, est → fr
      • ä ö ü ß + words like Datei, und, ist → de
      • ã õ ç + words like arquivo, está, para → pt
      • ñ + Spanish words (archivo, está, con) → es
      • ı ş ğ ç + Turkish words (dosya, için, çalış) → tr
      • Otherwise → en

    When the message is mixed or ambiguous, default to en. Write the chosen code to .claude/handoff/lang (no newline) using your file-write tool. Subsequent saves reuse the persisted value unless the user explicitly asks to switch language.

Read the full file on GitHub · 254 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 254 lines · 208 tokens per session scan C 0fc4f889ad7e

Subscribe to this mod's changes

handoff-revive is a skill published in the GitHub repository sofumel/claude-handoff-revive (6 stars, last pushed 2mo ago), licensed MIT. It adds 208 tokens to every session and 5,616 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Memory and contextcheckpointcontexthandoffpluginrate-limitresume
Related

Other skills, from other repositories

recall-assistant

Proactive context recovery, highlight sharing, and session linking for the recall plugin. Detects context loss, suggests /recall commands, flags findings for connected sessions, and translates natural language into recall operations. Enable with /recall config skillenabled true.

bledden/claude-recall-plugin · 56 tokens

sitrep

Situational awareness — where am I, what was I doing, what's next. Context recovery after compression, confusion, or mid-session reorientation.

martineserios/thebrana · 32 tokens

close

End a session — extract learnings, write handoff, store patterns, detect doc drift. Use when ending a work session or when the user says done/bye/closing.

martineserios/thebrana · 38 tokens

obsidian-resume

Resume a previous session from an Obsidian Session Handoff block.

lyupro/skillforge-mcp · 19 tokens

context-cycle-proactive

At 80-90% context, save to the brain, route to the right channel, load fresh context, and resume. Built-in lifecycle so every agent stays synced to the second brain and never drops work.

Gentech-Labs/genTech-agent-kit · 48 tokens

context-memory

Saves and searches past Claude Code sessions so context, decisions, and code persist across conversations. Use when user says 'remember this', 'save this session', 'recall', 'search past sessions', 'what did we discuss about', or 'find previous work on'. Do NOT use for general file storage, note-taking, or bookmark…

ErebusEnigma/context-memory · 73 tokens