handoff

handoff is a skill for Claude Code from ggombee/code-forge. It costs 85 tokens per session (1,122 once invoked), scanned A, original, MIT.

A session handoff tool that records important progress in a Markdown file and prepares a prompt for the next coding session. It preserves decisions, unfinished work, environment changes, and open questions.

In plain words
What is it for?
It helps document completed and remaining work, record questions that need an answer, update a chosen progress document, and copy a ready-to-use continuation prompt.
Why use it?
It reduces the chance of losing context when a session ends or becomes too long to continue comfortably.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the code-forge plugin — 39 skills, 14 agents, 11 hooks, 2 MCP servers shipped together

Good fit It helps document completed and remaining work, record questions that need an answer, update a chosen progress document, and copy a ready-to-use continuation prompt.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ggombee/code-forge/handoff
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 ggombee/code-forge --skill handoff
Clone the repo
git clone --depth 1 https://github.com/ggombee/code-forge

Made for: Claude Code.

Or install code-forge, the plugin that ships this one along with the rest of its 39 skills, 14 agents, 11 hooks, 2 MCP servers.

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

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

agentmods 80×15 button for handoff

Your own site · 80×15
<a href="https://agentmods.dev/skills/ggombee/code-forge/handoff"><img src="https://agentmods.dev/badge/skills/ggombee/code-forge/handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,122 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 $0.00085 $0.01122
Opus 5.5 $0.00034 $0.00449
Sonnet 5.5 $0.00017 $0.00224
Haiku 4.5 $0.00009 $0.00112

Measured 1mo ago against content hash db8390b6bbf3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

skills/handoff/SKILL.md · 76 lines

What it actually says

/handoff

auto-compact(자동 요약) 대신 사용자 통제 문서화로 세션을 넘긴다. 컨텍스트의 어떤 부분이 중요한지는 모델의 요약기가 아니라 진행 문서가 결정한다.

끊는 쪽 절반(기록 + 킥오프 프롬프트)을 이 스킬이 자동화하고, 받는 쪽 절반은 session-init.sh의 progress.md 자동 주입(state-schema §5)이 담당한다.

[즉시 실행] 아래 워크플로우를 바로 실행하세요.

옵션

호출 동작
/handoff 기본 — .claude/state/progress.md에 핸드오프 블록 append
/handoff <진행문서경로> 지정 문서(예: REDESIGN_PROGRESS.md)의 ★CURRENT 섹션 교체 갱신

Phase 1 — 맥락 추출 (대화에서)

현재 세션 대화에서 다음 5가지를 추출:

  1. 완료 — 이번 세션에서 끝낸 것 (커밋 해시 포함)
  2. 잔여 — 하다 만 것 + 정확한 다음 단계
  3. 결정 대기 ⚠️ — 사용자 답변이 필요한 미결 질문
  4. 환경/전제 변화 — 다음 세션이 알아야 할 환경 사실 (모델/버전/플래그 — 변한 것만)
  5. 다음 첫 마디 — 새 세션에 붙여넣을 한 문장 명령

추출 원칙:

  • 파일에서 다시 읽을 수 있는 것(코드 내용, 문서 본문)은 적지 않는다 — 포인터만 (file:line)
  • 대화에만 존재하는 것을 우선 보존: 결정과 그 이유, 시도했다 버린 접근, 사용자가 말로 준 제약
  • 모호함이 있었으면 4섹션 패턴(설계결정/편차/트레이드오프/미결질문 ⚠️)으로 기록 — docs/contracts/state-schema.md §5

Phase 2 — 진행 문서 갱신

  • 기본: .claude/state/progress.md에 state-schema §5 포맷으로 새 블록 append
  • 진행 문서 지정 시: 해당 문서의 ★CURRENT(또는 최상단 현재 섹션)를 교체 갱신. 이전 ★CURRENT 내용은 문서 하단 히스토리 섹션으로 이동 — 삭제 금지 (정보보존)
  • 미결 질문은 ⚠️ 마커 필수 (session-init이 강조 노출)

Phase 3 — 킥오프 프롬프트 생성 + 클립보드 복사

아래 형식으로 생성:

<작업명> 이어가자. /clear 후 새 세션이야.
1. <진행 문서 경로> 의 ★CURRENT(최상단) 읽기 — <한 줄 상태 요약>.
2. 먼저 읽을 것: <파일 1-2개>
3. 잔여: <잔여 한 줄>. 보고 후 진행.
확인 받을 것: <결정 대기 항목, 없으면 생략>
가이드라인(불변): <프로젝트 불변 원칙 1줄>

Bash로 클립보드 복사 (시크릿/키 값 절대 포함 금지):

pbcopy <<'KICKOFF'
<생성한 프롬프트>
KICKOFF

Phase 4 — 마무리 안내

사용자에게 한 줄 보고:

progress.md 갱신 + 킥오프 프롬프트 클립보드 복사 완료. 이제 /clear 입력 후 ⌘V로 붙여넣으세요.

/clear는 사용자 전용 명령이라 모델이 대신 실행할 수 없다. 완전 자동화는 Forge Voice의 ⌘⇧K 매크로로 가능 — /clear 입력 + 클립보드(킥오프) 붙여넣기 + 제출을 단축키 하나로 (tools/forge-voice.lua, /voice setup 시 설치). 음성 셋업을 안 했으면 위 수동 2단계.

graceful skip

  • .claude/state/ 없음 → 생성 후 신규 작성
  • pbcopy 없음(비 macOS) → 프롬프트를 코드블록으로 출력하고 수동 복사 안내
  • 추출할 게 거의 없는 짧은 세션 → phase/next 두 줄만 기록 (4섹션 강제 금지)
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. 1mo ago First seen · 76 lines · 85 tokens per session scan A db8390b6bbf3

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository ggombee/code-forge (17 stars, last pushed yesterday), licensed MIT. It adds 85 tokens to every session and 1,122 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

new

Start a new session — save summary to memory, then mark as reset so next message gets a fresh greeting. OpenClaw-compatible. Triggers on /new, /reset, /agent:new, "nueva sesión", "new session", "reset".

crisandrews/ClawCode · 54 tokens

alive-morning

Morning briefing -- read all walnut states, surface priorities, inbox count, stale walnuts, people nudges.

alivecontext/alive · 24 tokens

fresh-start

Continue in a new chat without losing anything — writes a compact handoff to paste into a fresh conversation. Use whenever the user wants to move to a new chat or conversation, hits usage limits, says replies got slow or Claude forgets earlier details, or the conversation has grown long.

egorfedorov/claude-context-optimizer · 60 tokens

token-check

Estimate how many tokens a pasted text, an attached file or the conversation so far takes, what it means for the context window and usage limits, and how to cut it. Use when the user asks how big something is in tokens, why they keep hitting limits, or whether a file is too large to send.

egorfedorov/claude-context-optimizer · 66 tokens

ccc-resume-session

Load a saved session file from /.claude/sessions/ (latest, by date, or by path), read it fully, and brief project, state, what not to retry, blockers and next step before touching anything. Use when resuming work, continuing where you left off, or after a fresh session.

KevinZai/commander · 68 tokens

gut-sync

Use when a user resumes work and needs an orientation card without full human recall. Not for packaging context for another agent or session: use handoff. Never source or remote-system changes.

OutlineDriven/odin-claude-plugin · 40 tokens