Agent skill

Paseo Agent Handoff

by getpaseo in getpaseo/paseo

Hands off the current task, including context, decisions and failed attempts, to a fresh agent through Paseo by writing a self-contained briefing prompt and launching that agent.

Custom licenceAuto-check passedAgent Workflows

Install Paseo Agent Handoff

skills CLI
$ npx skills add getpaseo/paseo --skill paseo-handoff -a claude-code

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

GitHub CLI
$ gh skill install getpaseo/paseo paseo-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/getpaseo/paseo.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/paseo-handoff .claude/skills/paseo-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
paseo-handoff
GitHub stars
20k
Used in
1 other repo
Token cost
~606 tokens
SKILL.md length
258 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
Custom licence

At a glance

Hands off the current task, including context, decisions and failed attempts, to a fresh agent through Paseo by writing a self-contained briefing prompt and launching that agent.

  • Works in 3 steps: Agent profile — explicit profile name… → Isolation — "in a worktree" / "worktree"… → Task description — anything else the…
  • Passing a task along with full context to a separate agent
  • SKILL.md covers Prerequisites, Parsing arguments, The handoff prompt and Launch
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Because the receiving agent starts with no context of its own, the skill builds the handoff prompt as a complete briefing: an imperative task description plus whatever decisions, failed attempts and constraints matter, preserving the exact intent behind the original task, so an investigate-only request becomes an explicit instruction not to edit files, a fix becomes an instruction to implement it, and a refactor is marked as refactor rather than rewrite.

Before creating the receiving agent, it reads the paseo skill and calls list_profiles, matching an explicit profile name or choosing the profile whose notes best fit the work, falling back to Paseo's provider discovery when none fits. An isolation request such as working in a worktree creates a new workspace with that isolation and a short branch name derived from the task. The new agent is launched with a Handoff-prefixed title and the briefing as its initial prompt, and the skill explicitly does not wait or poll for it to finish, leaving it in the user's subagent track until they detach it manually.

When your agent uses it

  • Passing a task along with full context to a separate agent
  • Starting a fresh agent on an isolated worktree to continue current work
  • Handing off an investigate-only task without risking file edits

Example prompts

  • “Handoff this bug investigation to the debugging profile agent.”
  • “Hand this off to another agent in a worktree to implement the fix.”
  • “Hand this off, read-only, to a researcher agent to look into the root cause.”

Requirements

  • The paseo skill and its list_profiles and create_agent tools

Workflow steps

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

  1. Agent profile — explicit profile name first; otherwise choose the profile whose notes best match the work. Materialize it into…
  2. Isolation — "in a worktree" / "worktree" → create a workspace with isolation: "worktree", using a short branch name derived from the task.
  3. Task description — anything else the user said.

What it can do on your machine

Read from SKILL.md and the folder at commit 29db2b7. 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.

    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

Paseo Agent Handoff loads about 606 tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 258 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~44
When it runs · the whole SKILL.md, loaded when a task matches
~606

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 258 words (~606 tokens).

“Transfer the current task — context, decisions, failed attempts, constraints — to a fresh agent. The receiving agent starts with zero context, so the handoff prompt must be a self-contained briefing.”

— opening of SKILL.md by getpaseo, Custom licence
name
paseo-handoff
user-invocable
true

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/paseo-handoff of getpaseo/paseo.

Open the folder on GitHubat commit 29db2b7

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in getpaseo/paseo, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Paseo Agent 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.

Paseo Agent Handoff compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Paseo Agent Handoff this skillgetpaseo/paseo20k1 repos~606Automated safety check: PassCustom licence
Orca CLIstablyai/orca88k2 repos~593Automated safety check: PassMIT
MemPalace Task HandoffMemPalace/mempalace59k—~1.9kAutomated safety check: PassMIT
Agent Manager Fleet TUIYoanWai/agent-manager578—~1kAutomated safety check: PassApache-2.0
Seat Continuity and Handovermvschwarz/openrig6.2k—~2.5kAutomated safety check: PassApache-2.0
Harness Engineering10xChengTu/harness-engineering1021 repos~1kAutomated safety check: PassNone

Similar skills

  • Orca CLI

    stablyai/orca

    Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser…

    88k GitHub starsUsed in 2 repos~593 tokens
    Agent WorkflowsAuto-check passed
  • MemPalace Task Handoff

    MemPalace/mempalace

    Creates, hands off, claims, executes and closes agent tasks through the MemPalace logstream, with approval of the exact task before it is recorded.

    59k GitHub stars~1.9k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Agent Manager Fleet TUI

    YoanWai/agent-manager

    Runs several coding-agent CLIs as real tmux sessions in one terminal UI, color-coded by whether each is working, waiting, idle or blocked.

    578 GitHub stars~1k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Separates a stable agent seat's identity from its changing occupant, and records honest, two-part provenance whenever one occupant replaces another.

    6.2k GitHub stars~2.5k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Harness Engineering

    10xChengTu/harness-engineering

    Set up and improve harness engineering (AGENTS.md, docs/, lint rules, eval systems, project-level prompt engineering) for AI-agent-friendly codebases.

    102 GitHub starsUsed in 1 repo~1k tokens
    Agent WorkflowsAuto-check passed
  • Runs a side question or brainstorm in a parallel thread so it does not derail the main agent's current work, then optionally hands the result back.

    207 GitHub stars~1.2k tokensUpdated 7 days ago
    Agent WorkflowsAuto-check passed

More from getpaseo/paseo

  • Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.

    20k GitHub starsUsed in 1 repo~756 tokens
    Auto-check passed
  • Paseo Committee

    getpaseo/paseo

    Forms a two-agent committee with contrasting profiles to analyze a stuck problem in parallel, reconcile their views and return a consensus plan without editing files.

    20k GitHub starsUsed in 1 repo~496 tokens
    Auto-check passed
  • Paseo Help

    getpaseo/paseo

    Answers questions about the Paseo app, such as setup, providers, connectivity, updates and logs, by checking the current public docs and working out which daemon is involved.

    20k GitHub stars~1.6k tokensUpdated today
    Auto-check passed
  • Paseo Plugin Builder

    getpaseo/paseo

    Builds, installs and troubleshoots trusted local Paseo plugins, from lifecycle hooks and slash commands to screens, themes and timeline renderers.

    20k GitHub stars~9.4k tokensUpdated today
    Auto-check passed
  • Reference for managing Paseo's projects, workspaces, workspace scripts and agents through its MCP tools or CLI, across a local or remote daemon.

    20k GitHub stars~2.1k tokensUpdated today
    Auto-check passed

Categories

Questions about Paseo Agent Handoff

What does Paseo Agent Handoff do?

Hands off the current task, including context, decisions and failed attempts, to a fresh agent through Paseo by writing a self-contained briefing prompt and launching that agent. Because the receiving agent starts with no context of its own, the skill builds the handoff prompt as a complete briefing: an imperative task description plus whatever decisions, failed attempts and constraints matter, preserving the exact intent behind the original task, so an investigate-only request becomes an explicit instruction not to edit files, a fix becomes an instruction to implement it, and a refactor is marked as refactor rather than rewrite.

When should I use Paseo Agent Handoff?

Paseo Agent Handoff fits situations like: passing a task along with full context to a separate agent; starting a fresh agent on an isolated worktree to continue current work; handing off an investigate-only task without risking file edits.

How do I install Paseo Agent Handoff in Claude Code?

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

How do I install Paseo Agent Handoff in Codex?

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

Can I use Paseo Agent 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 getpaseo/paseo --skill paseo-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/paseo-handoff, .gemini/skills/paseo-handoff, .github/skills/paseo-handoff and .opencode/skills/paseo-handoff in your project.

What does Paseo Agent Handoff need to run?

SKILL.md names no scripts, command-line tools or credentials: Paseo Agent Handoff is instructions for the agent only. Our summary lists: The paseo skill and its list_profiles and create_agent tools.

Does Paseo Agent 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 Paseo Agent 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 Paseo Agent Handoff use?

Paseo Agent Handoff has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Paseo Agent Handoff use?

About 606 tokens (SKILL.md is roughly 2.4k 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 Paseo Agent Handoff?

Skills that share tags, products or a category with Paseo Agent Handoff: Orca CLI (stablyai/orca, 88k stars), MemPalace Task Handoff (MemPalace/mempalace, 59k stars), Agent Manager Fleet TUI (YoanWai/agent-manager, 578 stars) and Seat Continuity and Handover (mvschwarz/openrig, 6.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Paseo Agent Handoff?

getpaseo (a GitHub organization) maintains it in getpaseo/paseo, which has 20,202 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 8, 2026.

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