handoff

handoff is a skill for Claude Code from aldianriski/lean-flow. It costs 93 tokens per session (901 once invoked), scanned A, original, MIT.

A session handoff skill that saves the current work state, decisions, blockers, and next steps in a temporary document for another agent or a future session.

In plain words
What is it for?
Use it when pausing mid-task, transferring work to another agent, or preparing a future session to continue from the same state.
Why use it?
It prevents unfinished work from losing its context when a session ends, the task is blocked, or the conversation becomes too large.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the lean-flow plugin — 15 skills 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/aldianriski/lean-flow/handoff
Any agent
npx skills add aldianriski/lean-flow --skill handoff
Clone the repo
git clone --depth 1 https://github.com/aldianriski/lean-flow

Made for: Claude Code.

Or install lean-flow, the plugin that ships this one along with the rest of its 15 skills.

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/aldianriski/lean-flow/handoff.svg)](https://agentmods.dev/skills/aldianriski/lean-flow/handoff)
Your own site
<a href="https://agentmods.dev/skills/aldianriski/lean-flow/handoff"><img src="https://agentmods.dev/badge/skills/aldianriski/lean-flow/handoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 901 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 $0.00093 $0.00901
Opus 5 $0.00046 $0.00451
Sonnet 5 $0.00019 $0.00180
Haiku 4.5 $0.00009 $0.00090

Measured 6d ago against content hash 512a77dd5ce0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 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/handoff/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

handoff

Compact the current conversation into a handoff document so a fresh agent can continue without re-deriving everything. Transient, not durable — this is the conversation's working state, not a project record. Pairs with /prime: handoff out at session end → /prime + read the handoff in.

When to invoke

  • Context budget is running low and work is unfinished.
  • A task is blocked and the next session will resume it.
  • A deliberate stop mid-task, or a planned agent-to-agent handoff.

Not a substitute for /lean-doc-generator close (durable sprint record + CHANGELOG) or a commit.

Where it saves

Write to the OS temp directory, not the workspace — a handoff is throwaway and must not pollute the repo or git status. Resolve temp per platform:

  • Windows: $env:TEMP (e.g. C:\Users\<you>\AppData\Local\Temp)
  • macOS / Linux: $TMPDIR or /tmp

Filename: handoff-<short-slug>.md. Emit the absolute path so the next session can read it.

What goes in

  1. Goal / focus — what this work is trying to achieve. If the user passed an argument, treat it as the next session's focus and tailor the doc to it.
  2. State — what's done, what's in progress, what's left. Be concrete (files touched, decisions made).
  3. Next steps — the ordered list the next agent should start with.
  4. Blockers / open questions — anything unresolved, with what's needed to unblock.
  5. Suggested skills — which skills the next agent should invoke (e.g. /prime first, then /orchestrator to resume, /diagnose for the failing test).
  6. References — do not duplicate — point to durable artifacts by path or URL (PRDs, ADRs, the sprint file, commits, diffs, issues). Summarize only what is NOT already captured elsewhere.

Hard rules

  • Redact secrets — never write API keys, passwords, tokens, or PII into the doc.
  • Reference, don't copy — if it's already in a commit / ADR / sprint file / issue, link it; don't restate it.
  • Temp dir only — never write the handoff into the workspace or stage it in git.
  • Transient — the doc captures conversation state; durable decisions still belong in DECISIONS.md / CHANGELOG via /lean-doc-generator.

Read the full file on GitHub · 66 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. 6d ago First seen · 66 lines · 93 tokens per session scan A 512a77dd5ce0

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository aldianriski/lean-flow (5 stars, last pushed 7d ago), licensed MIT. It adds 93 tokens to every session and 901 once invoked, about $0.0005 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

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

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens