Agent skill

Handoff

by Avijit07x in Avijit07x/claude-db

Write a short handoff note for the next chat or a teammate, with what is done, what is open, what comes next and what was rejected and why.

Apache-2.0Auto-check passedDevelopment

Install Handoff

skills CLI
$ npx skills add Avijit07x/claude-db --skill handoff -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Avijit07x/claude-db handoff --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Avijit07x/claude-db.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/handoff .claude/skills/handoff && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
handoff
GitHub stars
232
Token cost
~898 tokens
SKILL.md length
497 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
Apache-2.0

At a glance

Write a short handoff note for the next chat or a teammate, with what is done, what is open, what comes next and what was rejected and why.

  • Works in 4 steps: Gather the facts → Write the note → Save it → …
  • The user ends a piece of work
  • SKILL.md covers 1. Gather the facts, 2. Write the note, 3. Save it and 4. Print it, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Handoff is an agent skill from Avijit07x/claude-db. Write a short handoff note for the next chat or a teammate, with what is done, what is open, what comes next and what was rejected and why. Saves it to project memory so the next chat sees it at the start, and prints it so it can be pasted into a message or a pull request. Use when the user ends a piece of work, switches tasks, or hands the project to someone.

Its SKILL.md is about 900 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Agent memory and Pull requests. It works with Anthropic API. The repository describes itself as: Free, open-source memory for Claude Code. Your own database, no cloud, no subscription. The licence is Apache-2.0.

When your agent uses it

  • The user ends a piece of work
  • Hands the project to someone

Example prompts

  • “/handoff”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Gather the facts
  2. Write the note
  3. Save it
  4. Print it

What it can do on your machine

Read from SKILL.md and the folder at commit f0e86be. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Handoff loads about 898 tokens when it runs. Until then it costs about 93 tokens; SKILL.md has 497 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~93
When it runs · the whole SKILL.md, loaded when a task matches
~898

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Avijit07x/claude-db at commit f0e86be, republished under its Apache-2.0 licence (© Avijit07x). 497 words, ~898 tokens.

Download SKILL.mdSave it as .claude/skills/handoff/SKILL.md (or your agent's skills folder).
name
handoff
description
Write a short handoff note for the next chat or a teammate, with what is done, what is open, what comes next and what was rejected and why. Saves it to project memory so the next chat sees it at the start, and prints it so it can be pasted into a message or a pull request. Use when the user ends a piece of work, switches tasks, or hands the project to someone.

Write a handoff note

1. Gather the facts

Run this from the project root to see what memory and git already know:

bash
claude-db catchup

Combine that with what happened in this chat. The chat is the best source for what was done and what is still open. The output fills gaps and checks dates. If it shows a Last handoff, that is the note you will carry forward in step 2.

2. Write the note

The first line is the title and has today's date. Get it with date '+%b %-d'. Then write at most 8 lines, each under about 200 characters. The next chat reads this note at its start, so every line costs context.

Handoff, Oct 7:
- Done: timers, queue, mail family.
- Open: PR #18 not merged.
- Next: ask which retries to change on the worker queue.
- Decided: retries stay at 3, because the queue already backs off.
- Rejected: a second worker pool, because it doubled the mail cost.
- Watch out: tests read dist/, so run the build first.
- State: branch v0.12, 4 files uncommitted, last commit 1db3638.

Lines:

  • Done, Open and Next are always there. One line each.
  • Decided, Rejected, Watch out and State only when there is something real to say. Never pad.
  • Rejected and Decided give the reason after "because". A rejected idea with no reason is not worth a line.
  • State comes from the catchup output, not from memory: the Branch line and the newest of the Recent commits. Add a pull request number only if this chat mentioned one.
  • Decided and Rejected start from Decisions and dead ends in the output, plus this chat.
  • Name real things: a file, a pull request number, a command, a decision. Do not write various changes.
  • Use only what this chat or the output showed. Mark anything you are unsure of with (guess).
  • If there is no clear next step, write - Next: no clear next step yet. Do not invent one.
  • Leave out secrets, tokens, passwords and personal data.

Carry forward. Keep a line from the previous handoff when it is still true and still matters, and add the date to it, for example (Oct 5). Drop what is finished or wrong. If the note is over 8 lines, shorten lines or drop the oldest finished ones. Never drop a Rejected line that is still true.

Show full SKILL.md (174 more words)Show less

3. Save it

Call the remember memory tool once, with these exact values:

  • text: the note
  • key: handoff
  • kind: context
  • tags: ["handoff"]

The key makes a new handoff replace the old one for this project, so there is one current note. The next chat sees it at the start under Last handoff. It is shown for 14 days. Only the first 8 lines are shown, each cut at about 220 characters.

4. Print it

Show the note in a code block so the user can paste it into a message or a pull request. Then say in one line that it was saved, and that it replaces any earlier handoff for this project.

If the memory tool is not available, still print the note and say it was not saved.

Sharing

A teammate sees the saved note when both of you use the same Postgres or MongoDB database. With the default SQLite file on one machine, the printed note is the way to share it.

Shipped with claude-db. It is replaced when claude-db updates.

© Avijit07x, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/handoff of Avijit07x/claude-db.

Open the folder on GitHubat commit f0e86be

Compare with similar skills

Handoff next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Handoff compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Handoff this skillAvijit07x/claude-db232—~898Automated safety check: PassApache-2.0
Perfupraullenchai/Rapid-MLX3.9k—~1.6kAutomated safety check: NotesCustom licence
Compact Memory Implementationsimbajigege/book2skills183—~2.5kAutomated safety check: PassMIT
GitHub Review Iterationprisma/orm48k—~2.2kAutomated safety check: PassApache-2.0
Cherry Studio PR ReviewCherryHQ/cherry-studio52k—~3.9kAutomated safety check: PassAGPL-3.0
Commit Context Lookuprohitg00/agentmemory29k—~522Automated safety check: PassApache-2.0

Similar skills

  • Perfup

    raullenchai/Rapid-MLX

    Autonomous performance optimization: research, PoC, benchmark, implement, review, PR

    3.9k GitHub stars~1.6k tokensUpdated today
    AI & LLM EngineeringAuto-check: notes
  • Compact Memory Implementation

    simbajigege/book2skills

    A developer guide to adding compact memory to an agent: when to trigger compaction, how to fork a compactor sub-agent, what the summary holds, and how to restore it.

    183 GitHub stars~2.5k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed
  • Official

    Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.

    48k GitHub stars~2.2k tokensUpdated today
    DevelopmentAuto-check passed
  • Cherry Studio PR Review

    CherryHQ/cherry-studio

    Reviews Cherry Studio branches, pull requests, commits, files and docs against the project's own architecture, naming, API-boundary and UI rules, report-only by default.

    52k GitHub stars~3.9k tokensUpdated today
    DevelopmentAuto-check passed
  • Commit Context Lookup

    rohitg00/agentmemory

    Traces a file, function or line back to the agent session behind its current commit, using git blame and a memory lookup, and reports only what the records show.

    29k GitHub stars~522 tokensUpdated today
    DevelopmentAuto-check passed
  • Official

    Runs the triage step of the review-framework loop: reads fetched PR review state, builds `review-actions.json`, validates it and renders `review-actions.md`.

    48k GitHub stars~995 tokensUpdated today
    DevelopmentAuto-check passed

More from Avijit07x/claude-db

  • Catchup

    Avijit07x/claude-db

    Answer "where did I stop?" for this project. An agent skill from Avijit07x/claude-db.

    232 GitHub stars~604 tokensUpdated yesterday
    Auto-check passed
  • Cdb Scan

    Avijit07x/claude-db

    Map this codebase into project memory — a code graph of every symbol and how they connect, plus a written profile of stack, layout, conventions and workflows.

    232 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed

Works with

Questions about Handoff

What does Handoff do?

Write a short handoff note for the next chat or a teammate, with what is done, what is open, what comes next and what was rejected and why. Handoff is an agent skill from Avijit07x/claude-db. Write a short handoff note for the next chat or a teammate, with what is done, what is open, what comes next and what was rejected and why.

When should I use Handoff?

Handoff fits situations like: the user ends a piece of work; hands the project to someone.

How do I install Handoff in Claude Code?

Run `npx skills add Avijit07x/claude-db --skill handoff -a claude-code`. Or copy the skill folder (skills/handoff in Avijit07x/claude-db) into .claude/skills/handoff in your project. Claude Code loads it when a task matches its description.

How do I install Handoff in Codex?

Run `npx skills add Avijit07x/claude-db --skill handoff -a codex`. Or copy the skill folder (skills/handoff in Avijit07x/claude-db) into .agents/skills/handoff in your project. Codex loads it when a task matches its description.

Can I use Handoff in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Avijit07x/claude-db --skill handoff -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/handoff, .gemini/skills/handoff, .github/skills/handoff and .opencode/skills/handoff in your project.

What does Handoff need to run?

SKILL.md names no scripts, command-line tools or credentials: Handoff is instructions for the agent only.

Does Handoff access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Handoff safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Handoff use?

Handoff is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Handoff use?

About 898 tokens (SKILL.md is roughly 3.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Handoff?

Skills that share tags, products or a category with Handoff: Perfup (raullenchai/Rapid-MLX, 3.9k stars), Compact Memory Implementation (simbajigege/book2skills, 183 stars), GitHub Review Iteration (prisma/orm, 48k stars) and Cherry Studio PR Review (CherryHQ/cherry-studio, 52k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Handoff?

Avijit07x (a GitHub user) maintains it in Avijit07x/claude-db, which has 232 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 8, 2026.

Source: Avijit07x/claude-db on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.