handoff-prompt

handoff-prompt is a skill for Claude Code from muhimu/claude-plan-lifecycle. It costs 64 tokens per session (642 once invoked), scanned A, original, MIT.

A guide for creating a self-contained prompt that lets work continue in a new coding-agent session. It collects the relevant plan, design, files, decisions, caveats, and commands into one handoff.

In plain words
What is it for?
Use it after planning or brainstorming when handing implementation to a fresh session, including the plan paths, summary, starting task, and build or test commands.
Why use it?
It prevents important context from being lost when a session ends or is cleared. The next agent can begin with the project's current decisions and a concrete first action.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

Part of the plan-lifecycle plugin — 3 skills, 5 commands shipped together

Good fit Use it after planning or brainstorming when handing implementation to a fresh session, including the plan paths, summary, starting task, and build or test commands.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/muhimu/claude-plan-lifecycle/handoff-prompt
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 muhimu/claude-plan-lifecycle --skill handoff-prompt
Clone the repo
git clone --depth 1 https://github.com/muhimu/claude-plan-lifecycle

Made for: Claude Code.

Or install plan-lifecycle, the plugin that ships this one along with the rest of its 3 skills, 5 commands.

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-prompt

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/muhimu/claude-plan-lifecycle/handoff-prompt"><img src="https://agentmods.dev/badge/skills/muhimu/claude-plan-lifecycle/handoff-prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 642 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 $0.00064 $0.00642
Opus 5 $0.00032 $0.00321
Sonnet 5 $0.00013 $0.00128
Haiku 4.5 $0.00006 $0.00064

Measured 10d ago against content hash 18b054393ea9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

handoff-prompt 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.

skills/handoff-prompt/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Handoff Prompt

Generate a self-contained prompt for a new Claude Code session to execute work from the current conversation.

When to Use

  • User says "give me a prompt for a new session"
  • User says "handoff prompt" or "clean context prompt"
  • Planning/brainstorming is done, user wants fresh context for implementation
  • User wants to continue work after /clear

Process

  1. Gather from current conversation:

    • Plan file path and design spec path (if any)
    • 2-3 sentence summary of what to implement
    • Starting point (which task, what to do first)
    • Key decisions and caveats the new session must know
    • Build/test/lint commands
  2. Write a prompt with these sections:

    • What to do (1-2 sentences)
    • Files to read first (plan, spec — with full paths)
    • Summary (what the plan does, in brief)
    • Start by (first concrete action)
    • Key context (bullet list of decisions, caveats, gotchas that aren't in the plan files)
  3. Output the prompt in a fenced block so the user can copy-paste it.

Template

Implement [feature/change] for [project context].

- **Design spec:** `[path]`
- **Implementation plan:** `[path]`

**Summary:** [2-3 sentences of what the plan does]

**Start by:** [First concrete action — e.g., "Read both files, then execute Task 1 (revert commit X). Create a feature branch first."]

**Key context:**
- [Decision or caveat not obvious from the plan]
- [Another one]
- [Build/test commands if non-standard]

Rules

  • The prompt must be self-contained — the new session has zero context from this conversation
  • Reference file paths, not conversation content — the new session can read files but can't see our chat
  • Include only context that ISN'T already in the plan/spec files — don't duplicate
  • Do NOT restate rules already in global/project CLAUDE.md, AGENTS.md, or GEMINI.md. The new session loads these automatically. Examples to omit: branch naming conventions, commit message rules (no Co-Authored-By, no Claude footer), worktree locations, plan file locations, "never commit to main", subagent rules. If you're tempted to write a "Conventions" or "Ground rules" section that just echoes global preferences, delete it.
  • Keep it under 300 words — long prompts waste the new session's context
  • Don't include implementation details — that's what the plan file is for

Read the full file on GitHub · 61 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 First seen · 61 lines · 64 tokens per session scan A 18b054393ea9

Subscribe to this mod's changes

handoff-prompt is a skill published in the GitHub repository muhimu/claude-plan-lifecycle (2 stars, last pushed 9d ago), licensed MIT. It adds 64 tokens to every session and 642 once invoked, about $0.0003 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.