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

Team Handoff

by openclaw in openclaw/agent-skills

Hand local work to a shared OpenClaw Gateway: start a worktree session there as yourself in one request, seeded with a handoff, and get the session URL back.

MITAuto-check passedDevelopment

Install Team Handoff

skills CLI
$ npx skills add openclaw/agent-skills --skill team-handoff -a claude-code

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

GitHub CLI
$ gh skill install openclaw/agent-skills team-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/openclaw/agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/team-handoff .claude/skills/team-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
team-handoff
GitHub stars
1.1k
Token cost
~1.3k tokens
SKILL.md length
556 words
Files
2 (incl. scripts)
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Hand local work to a shared OpenClaw Gateway: start a worktree session there as yourself in one request, seeded with a handoff, and get the session URL back.

  • Works in 3 steps: Operator config, outside any repo → Isolated CLI profile so the local… → The human logs in once per Access…
  • Tasks that involve Git worktrees
  • SKILL.md covers Setup (once per machine), Use, Payload and Failure modes, plus 2 more sections
  • Runs Shell scripts from its folder; calls bash and cloudflared

What it does

Team Handoff is an agent skill from openclaw/agent-skills. Hand local work to a shared OpenClaw Gateway: start a worktree session there as yourself in one request, seeded with a handoff, and get the session URL back.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/team-handoff.sh`).

It sits in Development, covering Git worktrees. The repository describes itself as: Useful skills for agents and claws. The licence is MIT.

When your agent uses it

  • Tasks that involve Git worktrees

Example prompts

  • “/team-handoff”

Requirements

  • A Bash shell

Workflow steps

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

  1. Operator config, outside any repo
  2. Isolated CLI profile so the local Gateway config is never touched. The script
  3. The human logs in once per Access session lifetime (agents cannot)

What it can do on your machine

Read from SKILL.md and the folder at commit 7e73306. 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

    Ships 1 file in scripts/ (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • bash
    • cloudflared

    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

Team Handoff loads about 1.3k tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 556 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
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); the scripts in this folder are not scanned.

SKILL.md

The full file from openclaw/agent-skills at commit 7e73306, republished under its MIT licence (© openclaw). 556 words, ~1,259 tokens.

Download SKILL.mdSave it as .claude/skills/team-handoff/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
team-handoff
description
Hand local work to a shared OpenClaw Gateway: start a worktree session there as yourself in one request, seeded with a handoff, and get the session URL back.

Team Handoff

Use when the user says "open a session on the team server for this", "hand this off to <team agent>", or "summarize this for a new agent and start it on <gateway>", and the target is a shared OpenClaw Gateway behind an identity-aware proxy (Cloudflare Access).

One Gateway request, as the operator's own identity. No browser automation, no SSH, no polling.

Script: scripts/team-handoff.sh

Setup (once per machine)

  1. Operator config, outside any repo: ${XDG_CONFIG_HOME:-~/.config}/openclaw/team-handoff.env

    sh
    OPENCLAW_HANDOFF_URL=https://gateway.example      # the shared Gateway's public origin
OPENCLAW_HANDOFF_AGENT=main                        # default agent id on that Gateway
OPENCLAW_HANDOFF_PROJECT=example-project           # default projects.list id
# optional:
# OPENCLAW_HANDOFF_CLI=/path/to/openclaw           # installed OpenClaw CLI (default: openclaw on PATH)
# OPENCLAW_HANDOFF_PROFILE_DIR=~/.openclaw/profiles/team
# OPENCLAW_HANDOFF_SSH_HOST=gateway-host           # operator fallback only; see below

  2. Isolated CLI profile so the local Gateway config is never touched. The script writes it on first probe when missing: OPENCLAW_STATE_DIR and OPENCLAW_CONFIG_PATH point at the profile dir, whose openclaw.json holds only gateway.mode: "remote", gateway.remote.url, and an exec secret provider that runs cloudflared access token -app=<url> for the Cf-Access-Token header (gateway.remote.edgeAuth, see the OpenClaw docs page "Remote access", section "Gateway behind an identity-aware proxy"). The provider command must be the real cloudflared binary, not a symlink.

  3. The human logs in once per Access session lifetime (agents cannot):

    sh
    cloudflared access login https://gateway.example

    probe prints ok when the chain works. Exec provider "cloudflare-access" exited with code 1 or an HTTP 302 on upgrade means the login lapsed: ask the human to run it again; do not switch to the SSH fallback on your own.

Why there is no token to mint: with gateway.auth.mode: "trusted-proxy" the proxy authenticates the user and the Gateway maps the identity header to scopes; first connection auto-pairs a CLI device with the proxy's deviceAutoApprove scopes, which cover sessions.create.

Use

sh
bash scripts/team-handoff.sh probe
bash scripts/team-handoff.sh create \
  --label "Installed-package entry cap durable fix" \
  --name tree-cap-fix --base origin/main \
  --message-file /path/to/handoff.md
bash scripts/team-handoff.sh status <sessionKey>
bash scripts/team-handoff.sh archive <sessionKey> <sessionId>

create prints url: in the Control UI form <origin>/chat/<agent>/<label-slug>-<session-key-uuid-without-dashes>, plus the session key and run id. Hand the human that URL. Creation returns before the worktree is prepared; running with worktree: null right after is normal, and the agent's first turn starts once the checkout binds. Read status once; do not loop.

Show full SKILL.md (259 more words)Show less

Payload

  • Branch first. Push the work, pass --base <branch>, keep the long handoff in the branch (for example .openclaw/handoff.md); the message is then three lines: what the branch is, what to do first, what not to do. Local files are unreachable from the Gateway; commit them or summarize the numbers.
  • Without a branch, the whole handoff goes in --message-file: a one-line title first (it becomes the session title and URL slug), then goal, verified facts with numbers, owner files, the agreed plan and order, proof expectations, and explicit non-goals.
  • Name scope boundaries when a local session keeps part of the work, so two agents do not open duplicate PRs.

Failure modes

  • managed worktree allocation lease .../capacity was lost: the Gateway lost its worktree capacity lease during a slow project refetch. A retry in the same session then fails with branch already exists: openclaw/<name> because the failed attempt leaked its branch. Create a new session with a different --name; archive the dead one.
  • chat.send requires idempotencyKey; sessions.patch lifecycle changes require expectedSessionId.

SSH operator fallback

--via ssh runs the same sessions.create on the Gateway host as the Gateway's service user (OPENCLAW_HANDOFF_SSH_HOST, OPENCLAW_HANDOFF_REMOTE_CLI, OPENCLAW_HANDOFF_REMOTE_USER). The session is then owned by the operator identity, not the human. Use only when the human asks for it; never change Gateway config or restart anything from this path.

Don'ts

  • Do not drive the Gateway's web UI from an agent browser or sign in to the identity provider.
  • Do not point the machine's primary openclaw.json at the shared Gateway.
  • Do not poll session history in a loop.

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

Files

SKILL.md and 1 other file (scripts) in skills/team-handoff of openclaw/agent-skills.

  • SKILL.md
  • scripts/team-handoff.sh

Open the folder on GitHubat commit 7e73306

Compare with similar skills

Team 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.

Team Handoff compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Team Handoff this skillopenclaw/agent-skills1.1k—~1.3kAutomated safety check: PassMIT
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
Migrate Core Code to Submodulestinyhumansai/openhuman42k—~2.6kAutomated safety check: PassGPL-3.0
Finishing A Development Branchfarm-fe/farm5.6k34 repos~1.8kAutomated safety check: PassMIT
Git Worktree Cleanuplobehub/lobehub83k—~2.8kAutomated safety check: PassCustom licence
Keep Codex Fastvibeforge1111/keep-codex-fast1.6k—~3.1kAutomated safety check: PassMIT

Similar skills

  • Finishing a Development Branch

    obra/superpowers

    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.

    297k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed

  • Migrate Core Code to Submodules

    tinyhumansai/openhuman

    Plans and carries out moving non-host-specific code and its tests from the OpenHuman core into vendored tiny submodule libraries, then releases the submodule and re-pins the host.

    42k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed

  • Finishing A Development Branch

    farm-fe/farm

    A skill your agent uses when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for…

    5.6k GitHub starsUsed in 34 repos~1.8k tokens
    DevelopmentAuto-check passed

  • Git Worktree Cleanup

    lobehub/lobehub

    Audits stale Git worktrees and branches with a bundled script, classifies each one, and deletes only after you approve the exact candidates.

    83k GitHub stars~2.8k tokensUpdated today
    DevelopmentAuto-check passed

  • Keep Codex Fast

    vibeforge1111/keep-codex-fast

    A skill your agent uses when Codex feels slow or bloated, when local sessions/logs/worktrees/config have grown over time, or when a user wants safe maintenance for Codex Desktop/CLI state.

    1.6k GitHub stars~3.1k tokensUpdated 5 mo ago
    DevelopmentAuto-check passed

  • Pre-Release PR Triage

    jamiepine/voicebox

    Sorts a backlog of open pull requests into must-merge, candidate, superseded and deferred, writes a triage doc and works the merge loop before a release.

    57k GitHub stars~3.1k tokensUpdated 2 days ago
    DevelopmentAuto-check passed

More from openclaw/agent-skills

  • Beam

    openclaw/agent-skills

    Publish a redacted local coding session to an authenticated read-only Beam catalog.

    1.1k GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed

  • Session Viewer

    openclaw/agent-skills

    Render Codex, Claude Code, OpenClaw, or Pi session JSONL transcripts as a searchable, shareable single-file HTML viewer.

    1.1k GitHub stars~918 tokensUpdated 2 days ago
    Auto-check passed

  • Behavior Validator

    openclaw/agent-skills

    Source-blind user behavior validation against a prewritten contract for apps, CLIs, APIs, and generated artifacts.

    1.1k GitHub stars~940 tokensUpdated 2 days ago
    Auto-check passed

  • Crabbox Remote Test Runner

    openclaw/agent-skills

    Detects the Crabbox CLI or config in a repository and uses it to run tests and validation on remote runners, with checks before touching secrets or paid infrastructure.

    1.1k GitHub stars~3.6k tokensUpdated 2 days ago
    Auto-check passed

  • Handoff

    openclaw/agent-skills

    Clipboard-ready handoff prompt for another agent to investigate or continue a task.

    1.1k GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed

  • Readme Standard

    openclaw/agent-skills

    House README standard: structure, badge row, tone, per-archetype templates, and verification gates for steipete/openclaw repos.

    1.1k GitHub stars~1.4k tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about Team Handoff

What does Team Handoff do?

Hand local work to a shared OpenClaw Gateway: start a worktree session there as yourself in one request, seeded with a handoff, and get the session URL back. Team Handoff is an agent skill from openclaw/agent-skills. Hand local work to a shared OpenClaw Gateway: start a worktree session there as yourself in one request, seeded with a handoff, and get the session URL back.

When should I use Team Handoff?

Team Handoff fits situations like: tasks that involve Git worktrees.

How do I install Team Handoff in Claude Code?

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

How do I install Team Handoff in Codex?

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

Can I use Team 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 openclaw/agent-skills --skill team-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/team-handoff, .gemini/skills/team-handoff, .github/skills/team-handoff and .opencode/skills/team-handoff in your project.

What does Team Handoff need to run?

Going by SKILL.md and its folder, Team Handoff needs a shell for the scripts in its folder and the command-line tools its instructions call (bash and cloudflared). Our summary lists: A Bash shell.

Does Team 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 Team 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Team Handoff use?

Team 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 Team Handoff use?

About 1.3k tokens (SKILL.md is roughly 5k 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 Team Handoff?

Skills that share tags, products or a category with Team Handoff: Finishing a Development Branch (obra/superpowers, 297k stars), Migrate Core Code to Submodules (tinyhumansai/openhuman, 42k stars), Finishing A Development Branch (farm-fe/farm, 5.6k stars) and Git Worktree Cleanup (lobehub/lobehub, 83k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Team Handoff?

openclaw (a GitHub organization) maintains it in openclaw/agent-skills, which has 1,104 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 7, 2026.

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