Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Handoff

ASecurity

Save and copy a continuation prompt before /clear or switching harnesses.

10 stars
0 votes
0 copies
1 views
Added 10/4/2026
ai-agentspythongoshellbashgitdocumentation

Works with

claude codecli

Security Analysis

A100/100

Scanned 10/6/2026

$npx -y skills add fmind/dot --skill handoff --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Handoff?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Handoff
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/fmind-handoff/badge)](https://www.skillsdirectory.com/skills/fmind-handoff)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: handoff
description: "Save and copy a continuation prompt before /clear or switching harnesses."
license: MIT
metadata:
  kind: task
  author: Médéric HURIER (Fmind)
  source: github.com/fmind/dot/tree/main/skills/handoff
  created: "2026-10-04"
  updated: "2026-10-05"
---

# Handoff

Treat `/handoff` as "I am about to clear this session or move to another harness; let the next one continue without me re-explaining." It writes a continuation in the [task-prompts](../task-prompts/SKILL.md) format, saves it, and copies it with [clipboard](../clipboard/SKILL.md). Arguments can name a focus, a receiving harness, or `pointer` to copy only the file reference. Native resume (`claude --resume`, `codex resume`, or `codex fork` to branch) is better when the same harness continues with the full history.

## Workflow

1. **Freeze the state**: `git status --short --branch`, `git rev-parse --short HEAD`, staged versus unstaged work, worktrees, and anything still running: background shells, servers, monitors, subagents, scheduled wakeups. Stop nothing; record what is running, its handle or PID, and how to check on it.
1. **Write the continuation** from the [prompt template](../task-prompts/references/prompt-template.md). When space is short, keep in this order: objective and authority, the user's latest corrections and rejected approaches (quoted when the wording matters), current state with proof and the next step as an imperative, failed approaches, then the paths, logs, and running-work handles the next session needs, citing paths and lines instead of pasting code. Omit tool narration, passing logs, and anything the repository or AGENTS.md already states. Write it for a reader without this conversation; never include secrets or private passages. End with this fixed block, because the receiving session will not have this skill loaded:

   ```markdown
   ## Resume

   Read this whole file. Compare `git status --short --branch` and `git rev-parse --short HEAD` with the recorded state and report any drift before acting. Reuse recorded proof only while its inputs are unchanged, start at the next step, and keep the recorded authority boundaries. Delete this file once the work lands; it is task-owned scratch.
   ```

1. **Save**: in a repository, `.agents/prompts/<YYYY-MM-DD>-handoff-<slug>.md` under `git rev-parse --show-toplevel` (gitignored globally); outside one, `~/.agents/prompts/`. Never overwrite an existing handoff; add a suffix.
1. **Copy**: send the file itself, which avoids quoting the content into a shell command. With `pointer`, or when the prompt exceeds about 8,000 characters, copy one line instead: `Continue from <absolute path>: read it fully, verify the recorded state, then do the next step.`

   ```bash
   python -I ~/.agents/skills/clipboard/scripts/copy.py < "$handoff"
   ```

1. **Confirm**: the saved path, what was copied (full prompt or pointer), and anything still running that the user should know about before clearing.

## Gotchas

- **Authority does not grow**: a handoff records approvals already given; it never turns a proposal into an authorized action.
- **Record staged selections exactly**: the next session must not restage or commit unrelated work.
- **Flag running work for restart**: a background job started by this session may die with it; say whether it must be restarted.

## Documentation

- [Claude Code sessions](https://code.claude.com/docs/en/common-workflows#resume-previous-conversations) · [Codex resume](https://developers.openai.com/codex/cli/reference)
- Companion skills: [task-prompts](../task-prompts/SKILL.md) (prompt grammar and delegation), [clipboard](../clipboard/SKILL.md) (verified copy), [git-worktree](../git-worktree/SKILL.md) (isolated continuation).

Attribution

fmindfmind
View sourceSee grades on GitHubMore from fmind →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →