Agent skill

Handover

by ploxc in ploxc/modbux

Empty a session into files before its context goes — decide with the user what gets written down, write it, and only then say what the next session needs.

MITAuto-check passedDevelopment

Install Handover

skills CLI
$ npx skills add ploxc/modbux --skill handover -a claude-code

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

GitHub CLI
$ gh skill install ploxc/modbux handover --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/ploxc/modbux.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/handover .claude/skills/handover && 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
handover
GitHub stars
109
Token cost
~1.3k tokens
SKILL.md length
772 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Empty a session into files before its context goes — decide with the user what gets written down, write it, and only then say what the next session needs.

  • Works in 5 steps: Inventory, by destination → Put it to the user, item by item → Write the ones that were kept → …
  • The user says handover
  • SKILL.md covers 1. Inventory, by destination, 2. Put it to the user, item by…, 3. Write the ones that were kept and 4. Draft the prompt —…, plus 2 more sections
  • Calls git

What it does

Handover is an agent skill from ploxc/modbux. Empty a session into files before its context goes — decide with the user what gets written down, write it, and only then say what the next session needs. Use when the user says "handover", "compact", "wrap this up" or "start clean". Do NOT use to record one thing, which decides one destination and is todo.

Its SKILL.md is about 1.3k 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. The repository describes itself as: Free open-source Modbus client (master) GUI and server simulator for Windows, macOS and Linux. Desktop tool for Modbus TCP, RTU and RTU over TCP. A modern alternative to Modbus… The licence is MIT.

When your agent uses it

  • The user says handover
  • Record one thing
  • Which decides one destination and is todo

Example prompts

  • “handover”
  • “compact”
  • “wrap this up”
  • “/handover”

Workflow steps

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

  1. Inventory, by destination
  2. Put it to the user, item by item
  3. Write the ones that were kept
  4. Draft the prompt — new-session path
  5. Ask for the next instruction

What it can do on your machine

Read from SKILL.md and the folder at commit 3313c0f. 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

    Shell commands in SKILL.md call:

    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Handover loads about 1.3k tokens when it runs. Until then it costs about 79 tokens; SKILL.md has 772 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~79
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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 ploxc/modbux at commit 3313c0f, republished under its MIT licence (© ploxc). 772 words, ~1,312 tokens.

Download SKILL.mdSave it as .claude/skills/handover/SKILL.md (or your agent's skills folder).
name
handover
description
Empty a session into files before its context goes — decide with the user what gets written down, write it, and only then say what the next session needs. Use when the user says "handover", "compact", "wrap this up" or "start clean". Do NOT use to record one thing, which decides one destination and is todo.

Emptying a session

A prompt is not storage. What this session learned goes in a file that a future session opens by itself. What a prompt carries is only what is true of this moment: which branch, what is uncommitted, what is running, what is next. All of that is worthless in a week.

Decide what gets written first. Draft the prompt from what is left over, never from what was interesting.

Two paths. /compact writes its own summary of the conversation, so step 4 has no reader on that path and step 4b replaces it.

nextsteps
/clear, or a new session1, 2, 3, 4, 5
/compact1, 2, 3, 4b, 5

1. Inventory, by destination

This fires when the context is nearly gone, so the early half of the session is the half you recall worst. Reconstruct before you list:

sh
git status -sb
git log --oneline -15          # what this session did, not main..HEAD
git diff --stat $(git merge-base main HEAD)..HEAD | tail -3

Then sort each item by where it belongs, not by how interesting it was. /todo owns the destinations: invoke it rather than deciding here. Two things it does not own:

what it iswhere it goes
state: branch, commits, what is green, what is runningthe prompt, or the compact paragraph
the next instructionthe user writes it, step 5

One question makes it mechanical. For each item: if a future session needed this and I were gone, where would it look? A file, then it goes in the file. Nowhere, because it only matters for the next hour, then the prompt. "It would ask me" is the item most likely to be dropped and the one that must be written.

2. Put it to the user, item by item

Not a summary. A list of decisions, each with where you propose to put it, as an AskUserQuestion: keep or drop, your answer first and labelled as the recommendation, and per option the argument for it and the strongest one against, including against the one you recommend.

The destination is not part of the question. Step 1 settled it.

Say plainly what you would drop. A session produces more observations than are worth keeping and the author is the worst judge of which.

3. Write the ones that were kept

Through precommit, like anything else. Being at the end of a session does not make a doc change cheaper to get wrong.

Finish this before drafting anything. A prompt written first absorbs whatever was inconvenient to file.

Show full SKILL.md (372 more words)Show less

4. Draft the prompt — new-session path

One fenced block, nothing else inside it, so it is copied in one gesture. Use a four-backtick fence: a three-backtick one closes early on the first fenced block inside the prompt.

  • Where the work is. Branch, what is committed and what is not, which suites were last green. Paste step 1's output; from memory this is the one part the next session cannot check.
  • What is in flight. A running agent, a branch waiting to merge.
  • What the repo already answers, by pointing: CLAUDE.md, CONTRIBUTING.md, TODO.md, the memory directory, the tracker artifact. If one of them is stale, fixing it was step 3.
  • What the next session should know before it judges the work. A claim of yours that is unmeasured, a round that is repairing its own repairs, a range too large to read at once. This is the only part with no file.
  • The next instruction, from step 5. Not your guess at it.

A prompt that explains something has a step-3 failure in it. "Watch out for X" means X has a home and you skipped it.

4b. Write the compact paragraph — compact path

One paragraph, and only what has no file may go in it. Nothing prints a standing list here, so the paragraph carries itself: state has files, the repo answers its own shape, and a sentence repeating either spends the space that was actually at risk.

What is left is a judgement about this session. Hand over the line to type and nothing else:

sh
/compact <the paragraph>

A paragraph that is only state means there is nothing to type. Say steps 1 to 3 hold it, and stop. Inventing a judgement to fill this is worse than leaving it empty.

5. Ask for the next instruction

Both paths. An AskUserQuestion in step 2's form.

Where the answer lands differs. On the new-session path it is the last bullet of step 4. After a compact it goes in TODO.md, because a paragraph nobody re-reads is not where an instruction belongs.

An answer that changes direction sends you back to step 3. Ending a session is a natural moment to change direction, and whoever has been inside the work is least able to see that.

© ploxc, MIT. 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 .claude/skills/handover of ploxc/modbux.

Open the folder on GitHubat commit 3313c0f

Compare with similar skills

Handover 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.

Handover compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Handover this skillploxc/modbux109—~1.3kAutomated safety check: PassMIT
Vercel Composition Patternssupabase/supabase111k59 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers296k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 59 repos~726 tokens
    DevelopmentAuto-check passed
  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    296k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed
  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed

More from ploxc/modbux

  • Audit

    ploxc/modbux

    Audit one area of Modbux against the eight criteria and write the findings to tmp/AUDIT-<area.md, changing no code.

    109 GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • Precommit

    ploxc/modbux

    Run the checklist before committing or merging — read the diff, lint, typecheck, the unit suite, the e2e specs the change touches, then report and commit.

    109 GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Prose

    ploxc/modbux

    Measure a sentence you just wrote against the thing it describes, then prune the block it lands in.

    109 GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • Todo

    ploxc/modbux

    Route something you want to record to the place that holds it — TODO.md, a GitHub issue, the memory directory, or the plan in flight.

    109 GitHub stars~898 tokensUpdated today
    Auto-check passed

Categories

Questions about Handover

What does Handover do?

Empty a session into files before its context goes — decide with the user what gets written down, write it, and only then say what the next session needs. Handover is an agent skill from ploxc/modbux. Empty a session into files before its context goes — decide with the user what gets written down, write it, and only then say what the next session needs.

When should I use Handover?

Handover fits situations like: the user says handover; record one thing; which decides one destination and is todo.

How do I install Handover in Claude Code?

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

How do I install Handover in Codex?

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

Can I use Handover 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 ploxc/modbux --skill handover -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/handover, .gemini/skills/handover, .github/skills/handover and .opencode/skills/handover in your project.

What does Handover need to run?

Going by SKILL.md and its folder, Handover needs the command-line tools its instructions call (git).

Does Handover access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Handover 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 Handover use?

Handover is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Handover use?

About 1.3k tokens (SKILL.md is roughly 5.2k 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 Handover?

Skills that share tags, products or a category with Handover: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 296k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Handover?

ploxc (a GitHub organization) maintains it in ploxc/modbux, which has 109 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 7, 2026.

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