New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Codewhale Session Handoff

by codewhale-hq in codewhale-hq/Codewhale

Writes a paste-ready handoff for the next agent session, opening with a state-check command block and separating done, suspected and blocked work.

MITAuto-check passedAgent Workflows

Install Codewhale Session Handoff

skills CLI
$ npx skills add codewhale-hq/Codewhale --skill cw-handoff -a claude-code

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

GitHub CLI
$ gh skill install codewhale-hq/Codewhale cw-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/codewhale-hq/Codewhale.git skills-src && mkdir -p .claude/skills && cp -r skills-src/docs/skills/cw-handoff .claude/skills/cw-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
cw-handoff
GitHub stars
41k
Token cost
~1.1k tokens
SKILL.md length
563 words
Files
1
Skills in repo
63
Repo updated
First seen
Licence
MIT

At a glance

Writes a paste-ready handoff for the next agent session, opening with a state-check command block and separating done, suspected and blocked work.

  • Works in 6 steps: Write it as a prompt the next agent can… → Open with the refresh block, not with… → Cover these, in whatever order fits;… → …
  • Ending a session with work still in flight
  • SKILL.md covers When to use, Workflow, Red flags / don't and Output
  • Calls git

What it does

The skill treats a handoff as a prompt the next agent can act on directly, not a report about the work, because that reader has none of the writer's context and every incentive to trust the prose. It opens with a refresh block of git commands (status, branch, recent log) that the reader should run and trust over anything written below it, rather than opening with a summary.

The body then covers, dropping any section that is empty: the repository path and expected branch, an authority line stating what the next session may do without asking (defaulting to no push, merge, tag, publish or destructive cleanup without approval), durable files to read such as the scoped AGENTS.md and specific docs the task touches, commits already landed with their SHAs, dirty worktree caveats naming the uncommitted files and whose they are, the next slices in priority order, the smallest correct verification gate for them, and any open decisions that genuinely belong to the person.

It insists on keeping done and verified, suspected, and blocked strictly separate, and treats anything not actually run as not done. It is stage six of a larger loop, feeding into a companion orient skill at the start of the next session.

When your agent uses it

  • Ending a session with work still in flight
  • Writing a branch takeover prompt for another agent or model
  • Handing a task to a fleet worker or a remote session
  • Summarizing current state for asynchronous continuation

Example prompts

  • “Write a handoff for the next session so they can continue this refactor.”
  • “I'm handing this branch to another agent. Write the takeover prompt.”
  • “Summarize what's done, suspected and blocked on this task before I end the session.”

Requirements

  • A git repository

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Write it as a prompt the next agent can paste directly. Not a report
  2. Open with the refresh block, not with your summary. The first thing the
  3. Cover these, in whatever order fits; drop sections that are empty
  4. Separate three states, and never blur them: done and verified (with the
  5. Say what the branch is for. Local-only, pushed for backup, or intended to
  6. Record missing external receipts. If the task was local-only, say which

What it can do on your machine

Read from SKILL.md and the folder at commit 8d2fb45. 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

Codewhale Session Handoff loads about 1.1k tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 563 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~57
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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 codewhale-hq/Codewhale at commit 8d2fb45, republished under its MIT licence (© codewhale-hq). 563 words, ~1,063 tokens.

Download SKILL.mdSave it as .claude/skills/cw-handoff/SKILL.md (or your agent's skills folder).
name
cw-handoff
description
Use when writing a Codewhale takeover prompt, continuation note, or end-of-session summary for another agent or a later session: a paste-ready handoff grounded in live state, with done/suspected/blocked kept separate.

cw-handoff

A handoff is read by an agent with none of your context and every incentive to believe you. That makes an optimistic handoff worse than no handoff: it converts your guesses into the next session's premises. Write it so the reader can re-derive the state instead of trusting the prose.

Stage 6 of the loop, and the one that makes the loop a loop: the next session starts at cw-orient with what you leave here.

When to use

  • Ending a session with work in flight.
  • Asked for "a prompt for another agent", branch takeover instructions, a continuation note, or a summary of current state for async work.
  • Handing a lane to a different model, a fleet worker, or a remote session.

Workflow

  1. Write it as a prompt the next agent can paste directly. Not a report about the work — instructions for continuing it.

  2. Open with the refresh block, not with your summary. The first thing the reader should do is verify you:

    bash
    cd <repo path>
git status --short --branch && git branch --show-current
git log --oneline --decorate -20
git worktree list
./scripts/release/check-versions.sh

    Tell them to trust that output over anything below it.

  3. Cover these, in whatever order fits; drop sections that are empty:

    • Repository path and expected branch or worktree.
    • The authority line: what they may and may not do without asking. Default to local-only — no push, merge, tag, publish, GitHub Release, or destructive cleanup without explicit approval.
    • Durable files to read, ordered by importance: the scoped AGENTS.md for the area, then the specific docs (docs/CACHE.md, docs/MOTION_CONTRACT.md, docs/ARCHITECTURE.md, crates/tui/AGENTS.md) the task actually touches.
    • Commits already landed, with SHAs.
    • Dirty worktree caveats, naming uncommitted files explicitly, and whose they are. This is the single most useful line in most handoffs.
    • The next slices, in priority order, each bounded the way cw-slice bounds one.
    • The verification gate for those slices — the smallest correct one from cw-gates, plus any known-flaky names.
    • Open decisions that genuinely belong to Hunter.

  4. Separate three states, and never blur them: done and verified (with the command output that proves it), suspected (a hypothesis, labeled), and blocked (with what unblocks it). If you did not run it, it is not done.

  5. Say what the branch is for. Local-only, pushed for backup, or intended to stay unpushed — the next agent cannot tell from git alone, and guessing wrong is how work gets force-pushed away.

  6. Record missing external receipts. If the task was local-only, say which evidence you could not gather (CI state, registry state, review threads) rather than inferring it. A named gap is useful; a confident guess is not.

Show full SKILL.md (146 more words)Show less

Red flags / don't

  • Don't imply publication happened unless you verified registry, tag, or release state live.
  • Don't hand off a narrative. Prefer concrete paths, commands, and SHAs.
  • Don't summarize away the dirt. Unnamed uncommitted files get destroyed.
  • Don't hand the next agent decisions you could have made. Reserve Hunter-facing choices for product direction, irreversible actions, and visual judgments that need eyes.
  • Don't copy a previous handoff's state forward. Re-derive it; that is what step 2 is for.
  • Don't include secrets, tokens, or provider credentials in a handoff file.

Output

A single paste-ready block with the default shape — refresh commands, authority line, files to read, landed SHAs, named dirty files, prioritized next slices, the verification gate, and the open decisions — with done / suspected / blocked visibly separated. Compress when trivial, but never compress away the state separation: that is what keeps guesses from becoming the next session's premises.

© codewhale-hq, 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 docs/skills/cw-handoff of codewhale-hq/Codewhale.

Open the folder on GitHubat commit 8d2fb45

Compare with similar skills

Codewhale Session 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.

Codewhale Session Handoff compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Codewhale Session Handoff this skillcodewhale-hq/Codewhale41k—~1.1kAutomated safety check: PassMIT
Beads Task Memorygastownhall/beads28k—~1.2kAutomated safety check: PassMIT
Session History Searchslopus/happy24k—~3.1kAutomated safety check: PassMIT
Auditopenwpm/OpenWPM1.4k—~676Automated safety check: PassCustom licence
MemorixAVIDS2/memorix837—~516Automated safety check: PassApache-2.0
Session Catchup and Handoffposhan0126/dotclaude871—~811Automated safety check: PassMIT

Similar skills

  • Beads Task Memory

    gastownhall/beads

    Tracks multi-session work with dependencies in the bd issue tracker so the agent can find ready tasks and recover its context after conversation compaction.

    28k GitHub stars~1.2k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Session History Search

    slopus/happy

    Searches past Claude Code, Codex and Cursor sessions and summarizes what was worked on, tried or decided, using extraction scripts instead of reading raw logs.

    24k GitHub stars~3.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Audit

    openwpm/OpenWPM

    A skill your agent uses when stuck, confused, or disoriented in a crosslink-tracked project — dumps the full context (session state, active issue, locks, blockers, hook config, git state, project…

    1.4k GitHub stars~676 tokensUpdated 5 days ago
    Agent WorkflowsAuto-check passed

  • Memorix

    AVIDS2/memorix

    A skill your agent uses when Claude Code needs Memorix shared memory, reasoning, Git Memory, mini-skills, session handoff, orchestration coordination, or integration troubleshooting.

    837 GitHub stars~516 tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Session Catchup and Handoff

    poshan0126/dotclaude

    Rebuilds working context after /clear by reading a handoff note and the branch's git state, or writes that handoff note before a session ends.

    871 GitHub stars~811 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

  • File-Based Planning in Arabic

    OthmanAdi/planning-with-files

    Arabic edition of a file-based planning skill that keeps task_plan.md, findings.md and progress.md on disk so multi-step agent work survives lost context.

    27k GitHub stars~3.2k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check: notes

More from codewhale-hq/Codewhale

All 63 skills in this repo

  • Codewhale Dogfood Install

    codewhale-hq/Codewhale

    Proves a Codewhale change in the real product: a stamped release build, an atomic local install, fresh-shell verification and manual QA that automated gates cannot cover.

    41k GitHub stars~1.3k tokensUpdated today
    Auto-check passed

  • Codewhale Landing Workflow

    codewhale-hq/Codewhale

    Decides how verified work should reach main, directly, in a worktree or on an integration branch, while keeping contributor credit and respecting merge gates.

    41k GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Sub-Agent Delegation

    codewhale-hq/Codewhale

    Guides when and how to split multi-step coding, research or verification work into focused sub-agent runs while the parent keeps integration and final checks.

    41k GitHub stars~790 tokensUpdated today
    Auto-check passed

  • Codewhale Fleet Manager

    codewhale-hq/Codewhale

    Triages and manages Codewhale fleet runs and workers with typed commands, classifying failures and choosing a safe restart, resume or escalation.

    41k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • GitHub Issue Bulk Assigner

    codewhale-hq/Codewhale

    Moves a list of GitHub issues into a milestone or assigns them to owners with the gh CLI, checking each one before and after the change.

    41k GitHub stars~953 tokensUpdated today
    Auto-check passed

  • Codewhale Issue Filing

    codewhale-hq/Codewhale

    Turns a bug or idea into a single actionable Codewhale GitHub issue with evidence, a gap-naming title, acceptance criteria and related links.

    41k GitHub stars~1.3k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Codewhale Session Handoff

What does Codewhale Session Handoff do?

Writes a paste-ready handoff for the next agent session, opening with a state-check command block and separating done, suspected and blocked work. The skill treats a handoff as a prompt the next agent can act on directly, not a report about the work, because that reader has none of the writer's context and every incentive to trust the prose. It opens with a refresh block of git commands (status, branch, recent log) that the reader should run and trust over anything written below it, rather than opening with a summary.

When should I use Codewhale Session Handoff?

Codewhale Session Handoff fits situations like: ending a session with work still in flight; writing a branch takeover prompt for another agent or model; handing a task to a fleet worker or a remote session; summarizing current state for asynchronous continuation.

How do I install Codewhale Session Handoff in Claude Code?

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

How do I install Codewhale Session Handoff in Codex?

Run `npx skills add codewhale-hq/Codewhale --skill cw-handoff -a codex`. Or copy the skill folder (docs/skills/cw-handoff in codewhale-hq/Codewhale) into .agents/skills/cw-handoff in your project. Codex loads it when a task matches its description.

Can I use Codewhale Session 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 codewhale-hq/Codewhale --skill cw-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/cw-handoff, .gemini/skills/cw-handoff, .github/skills/cw-handoff and .opencode/skills/cw-handoff in your project.

What does Codewhale Session Handoff need to run?

Going by SKILL.md and its folder, Codewhale Session Handoff needs the command-line tools its instructions call (git). Our summary lists: A git repository.

Does Codewhale Session Handoff 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 Codewhale Session 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 Codewhale Session Handoff use?

Codewhale Session Handoff 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 Codewhale Session Handoff use?

About 1.1k tokens (SKILL.md is roughly 4.3k 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 Codewhale Session Handoff?

Skills that share tags, products or a category with Codewhale Session Handoff: Beads Task Memory (gastownhall/beads, 28k stars), Session History Search (slopus/happy, 24k stars), Audit (openwpm/OpenWPM, 1.4k stars) and Memorix (AVIDS2/memorix, 837 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Codewhale Session Handoff?

codewhale-hq (a GitHub organization) maintains it in codewhale-hq/Codewhale, which has 41,078 GitHub stars. The repository holds 63 skills in this directory. The repository was last updated on October 9, 2026.

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