Orca CLI
stablyai/orca
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser…
Plan and document handoffs, parent lane contracts, and parallel batch contracts between specialized AI agents (foreman, workers, reviewers).
Install Multi Agent Handoff
$ npx skills add Arenukvern/mcp_flutter --skill multi-agent-handoff -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Arenukvern/mcp_flutter multi-agent-handoff --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Arenukvern/mcp_flutter.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/multi-agent-handoff .claude/skills/multi-agent-handoff && rm -rf skills-srcUse ~/.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/
Install the "multi-agent-handoff" agent skill from https://github.com/Arenukvern/mcp_flutter/tree/main/.agents/skills/multi-agent-handoff into .claude/skills/multi-agent-handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "multi-agent-handoff", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Arenukvern/mcp_flutter/tree/main/.agents/skills/multi-agent-handoffType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Arenukvern/mcp_flutter --skill multi-agent-handoff -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Arenukvern/mcp_flutter multi-agent-handoff --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Arenukvern/mcp_flutter.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/multi-agent-handoff .agents/skills/multi-agent-handoff && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "multi-agent-handoff" agent skill from https://github.com/Arenukvern/mcp_flutter/tree/main/.agents/skills/multi-agent-handoff into .agents/skills/multi-agent-handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "multi-agent-handoff", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Arenukvern/mcp_flutter --skill multi-agent-handoff -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Arenukvern/mcp_flutter multi-agent-handoff --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Arenukvern/mcp_flutter.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/multi-agent-handoff .cursor/skills/multi-agent-handoff && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "multi-agent-handoff" agent skill from https://github.com/Arenukvern/mcp_flutter/tree/main/.agents/skills/multi-agent-handoff into .cursor/skills/multi-agent-handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "multi-agent-handoff", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Arenukvern/mcp_flutter.git --path .agents/skills/multi-agent-handoff--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Arenukvern/mcp_flutter --skill multi-agent-handoff -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Arenukvern/mcp_flutter multi-agent-handoff --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Arenukvern/mcp_flutter.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/multi-agent-handoff .gemini/skills/multi-agent-handoff && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "multi-agent-handoff" agent skill from https://github.com/Arenukvern/mcp_flutter/tree/main/.agents/skills/multi-agent-handoff into .gemini/skills/multi-agent-handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "multi-agent-handoff", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Arenukvern/mcp_flutter multi-agent-handoffInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Arenukvern/mcp_flutter --skill multi-agent-handoff -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Arenukvern/mcp_flutter.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/multi-agent-handoff .github/skills/multi-agent-handoff && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "multi-agent-handoff" agent skill from https://github.com/Arenukvern/mcp_flutter/tree/main/.agents/skills/multi-agent-handoff into .github/skills/multi-agent-handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "multi-agent-handoff", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Arenukvern/mcp_flutter --skill multi-agent-handoff -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Arenukvern/mcp_flutter multi-agent-handoff --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Arenukvern/mcp_flutter.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/multi-agent-handoff .opencode/skills/multi-agent-handoff && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "multi-agent-handoff" agent skill from https://github.com/Arenukvern/mcp_flutter/tree/main/.agents/skills/multi-agent-handoff into .opencode/skills/multi-agent-handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "multi-agent-handoff", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
multi-agent-handoff- GitHub stars
- 386
- Token cost
- ~2.7k tokens
- SKILL.md length
- 1,060 words
- Files
- 8 (incl. references)
- Skills in repo
- 23
- Repo updated
- First seen
- Licence
- MIT
At a glance
Plan and document handoffs, parent lane contracts, and parallel batch contracts between specialized AI agents (foreman, workers, reviewers).
- Works in 6 steps: Isolate the minimal source-owned diff… → Apply only that diff to the owner… → Rerun the lane's native gate in the… → …
- Multi-agent workflows
- SKILL.md covers When to use, Handoff document template, Parallel batch contract and Parent lane contract, plus 6 more sections
- Calls npx
What it does
Multi Agent Handoff is an agent skill from Arenukvern/mcp_flutter. Plan and document handoffs, parent lane contracts, and parallel batch contracts between specialized AI agents (foreman, workers, reviewers). Use for multi-agent workflows, subagents, original goal preservation, native gates, claim ceilings, terminal states, baton passes, or guild-style agent coordination.
Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including reference files (for example `evals/cases/parallel-batch-contract-trigger.yaml`, `evals/cases/parallel-overhead-collapse-trigger.yaml` and `evals/cases/parallel-product-impact-guardrail-trigger.yaml`).
It sits in Agent Workflows, covering Multi-agent orchestration. The repository describes itself as: MCP Toolkit for Flutter AI Agent Driven Development (MCP/CLI + custom client side tools) - via closed feedback loop (visual & semantic snapshot) and high client side… The licence is MIT.
When your agent uses it
- Multi-agent workflows
- Original goal preservation
- Terminal states
- Guild-style agent coordination
Example prompts
- “/multi-agent-handoff”
Requirements
- Node.js
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Isolate the minimal source-owned diff from the temp or worker result.
- Apply only that diff to the owner checkout.
- Rerun the lane's native gate in the owner checkout.
- Update the current ledger or evidence note only if the claim changed.
- Record source_owner_status as temp_only,
- Mark the terminal state as integrated_to_owner, blocked_to_current_ledger,
What it can do on your machine
Read from SKILL.md and the folder at commit 62f3ee1. 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:
npx
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npx, 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
Multi Agent Handoff loads about 2.7k tokens when it runs, and up to ~3.9k if it reads all its reference files. Until then it costs about 82 tokens; SKILL.md has 1,060 words of instructions outside code blocks.
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 Arenukvern/mcp_flutter at commit 62f3ee1, republished under its MIT licence (© Arenukvern). 1,060 words, ~2,724 tokens.
Download SKILL.mdSave it as
.claude/skills/multi-agent-handoff/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.- name
- multi-agent-handoff
- description
- Plan and document handoffs, parent lane contracts, and parallel batch contracts between specialized AI agents (foreman, workers, reviewers). Use for multi-agent workflows, subagents, original goal preservation, native gates, claim ceilings, terminal states, baton passes, or guild-style agent coordination.
- license
- MIT
- type
- governance
- metadata.author
- skill-steward
- metadata.version
- 1.0.0
- metadata.category
- multi-agent
Multi-agent handoff
Structure work so multiple agents can execute sequentially without losing context.
When to use
- Splitting a large task across explorer, implementer, and reviewer agents
- Foreman/worker or parent/subagent patterns
- Need a written baton between chat sessions or tools
Handoff document template
Create or update HANDOFF.md (or a section in the task issue) with:
## Goal
{one sentence outcome}
## Done
- {completed items}
## Next
1. {ordered steps for the receiving agent}
## Constraints
- {tech stack, style, files not to touch}
## Verification
- {commands or checks that must pass}
## Validation status
- {commands run}
- {commands skipped or blocked, with reason}
- {blocked JSON explained with `steward blocked explain --input <path> --json`, when available}
- {schema/output drift checked with `steward schema check-outputs --json`, when machine-readable output is part of the handoff}
- {claims not proven because validation was skipped or blocked}
## Partial results
- {missing, partial, superseded, or timed-out agents/lenses}
## Context links
- {paths, PRs, prior decisions}
## Artifact capture
- {ADR, FAQ, skill, evidence note, test, validator, generator, or check that should absorb durable learning}Parallel batch contract
For broad decomposable work, the parent may use a disposable batch section instead of a new plan format. Keep only enough contract to move safely:
- original goal and user acceptance check;
- default native gate and aggregate gates;
- product impact check for the primary artifact, especially when the repo is an app, library, CLI/tool, plugin, or prototype;
- detour budget and stop condition;
- integration capacity, merge order, and conflict policy;
- comparison strategy for lane outputs;
- final evidence boundary, claim ceiling, and non-claims;
- acceleration note with three fields:
Saved,Cost/duplication, andFuture hot path; - hot-path promotion check for repeated verification or comparison work.
Use this compact shape before dispatching parallel lanes:
## Parallel Batch
Original goal: {user-visible outcome}
Acceptance check: {how the parent will know the original goal is satisfied}
Product impact check: {source-owned product behavior/API/UI/perf/doc-user workflow that must change or be proven unchanged}
Default native gate: {repo-native command or reason none exists}
Aggregate gate: {final validation before claiming completion}
Detour budget: {when to stop repairing tools and return to the goal}
Claim ceiling: {strongest claim allowed if all lanes pass}
Non-claims: {adjacent claims this batch cannot prove}
Acceleration note:
- Product impact line: {recognized prefix plus proof; use support_only: Steward scaffolding only when no product surface moved}
- Saved: {time, uncertainty, or risk reduced by running lanes in parallel}
- Cost/duplication: {duplicated work, integration cost, or coordination drag caused or avoided}
- Future hot path: {command, check, skill, script, deletion, or native route created for the next run}
| Lane | Agent/role | Scope | Write set | Forbidden paths | Native gate | Direct fix? | Terminal state |
|------|------------|-------|-----------|-----------------|-------------|-------------|----------------|
| L1 | {owner} | {bounded work} | `{paths}` | `{paths}` | `{command}` | yes/no | pending |Delete or collapse this batch section after synthesis unless it becomes a review artifact. Do not preserve lane maps as project management state.
Parent lane contract
Parent-assigned lane contracts are the only write-authority surface. Advisory ecology route dispatch_lane_candidates, MoE findings, A2A notes, and reviewer comments are inputs only.
Each assigned lane should state:
lane_id, assigned agent/role, scope, exactwrite_set, andforbidden_paths;- inherited repo rules, required impact checks, permission checks, native gate, and aggregate gate responsibility;
direct_fix_allowed: true|false, claim ceiling, non-claims, and escalation triggers;- terminal state:
integrated_to_owner,rejected,blocked_to_current_ledger,promoted_to_durable_owner,deleted,reported_to_parent,accepted_as_input,partial,timed_out, orsuperseded.
Only a parent lane contract may set direct_fix_allowed: true. Direct fixes must be bounded low-risk work with exact write sets, declared forbidden paths, inherited safety rules, required impact/permission checks, and available validation. If validation is skipped or blocked, the result downgrades to blocked or recommendation; it is not integrated_to_owner.
A2A artifacts never authorize writes, widen scope, accept/reject lanes, or launder steward judgment. The parent or explicit A2Human checkpoint owns authorization, synthesis, final claims, and scope changes.
Landing phase
When a lane proves a fix in a temp clone, fork, worktree, or external checkout,
that proof is accepted_as_input until the owner checkout carries the smallest
source-owned diff and reruns the native gate. Do not treat temp proof as
repo-owned evidence by default.
Before claiming a lane is integrated:
- Isolate the minimal source-owned diff from the temp or worker result.
- Apply only that diff to the owner checkout.
- Rerun the lane's native gate in the owner checkout.
- Update the current ledger or evidence note only if the claim changed.
- Record
source_owner_statusastemp_only,owner_landed_pending_gate,owner_gate_passed, orblocked_owner_dirty. - Mark the terminal state as
integrated_to_owner,blocked_to_current_ledger,accepted_as_input, orrejected.
If the source checkout is dirty or cannot accept the diff safely, record the temp proof as a candidate and keep the stronger source-owned claim unproven. After one bounded landing attempt, close the lane as blocked or rejected rather than creating another proof packet for the same unlanded result.
Show full SKILL.md (559 more words)Show less
Workflow
- Decompose — break the goal into independent slices where possible.
- Assign roles — e.g. Explore (read-only), Implement (write), Review (read-only critique).
- Write baton — fill the template; keep "Next" to ≤7 concrete steps. For parallel work, include the compact batch table before dispatch.
- Execute one slice — receiving agent does only "Next"; updates "Done".
- Record proof — update validation status before claiming completion. Skipped checks and blocked generators are non-proof, not quiet success.
- Land source-owned changes — convert temp or worker proof into the owner checkout and rerun the native gate before strengthening the claim.
- Close every lane — assign a terminal state to each lane or lens, including timed-out, blocked, or superseded work.
- Measure acceleration — fill the acceleration note with what was saved, what duplicated work or coordination cost appeared, and what future command/check/hot path now exists. If nothing was saved, say so and keep the claim ceiling low.
- Check product impact — for product repos, name the source-owned product
delta or product-native gate reached. If the batch only improved Steward
scaffolding, proof artifacts, or tools-about-tools, claim orientation or
harness maintenance only, not product acceleration.
Use one product impact prefix:
runtime_behavior:,public_api:,product_native_gate:,visual_capture:,performance_metric:,release_path:,developer_workflow:,command_output:,plugin_install:, orsupport_only:. IfCost/duplicationis not lower than the saved uncertainty, risk, or repeat work, default toleave_native,rejected, or a low-confidence support claim. - Capture durable learning — if a finding changes future behavior, route it to an ADR, FAQ, skill, evidence note, validator, generator, test, or check.
- Re-handoff — pass updated
HANDOFF.mdto the next agent or subagent. - Close — delete or archive handoff file when goal is verified.
Anti-patterns
- Vague "continue working on X" without file paths or acceptance criteria
- Handoffs longer than one screen (split into
references/or issues) - Duplicate conflicting instructions across parent and child agents
- Subagents that repeat the parent plan instead of looking for contradiction, stale assumptions, missing evidence, or smaller deletable designs
- Final handoffs that sound complete while validation is skipped, blocked, or only manually inferred
- Clean temp proof presented as source-owned adoption before landing and rerunning the owner checkout's native gate
- Long-running or vanished subagents silently absorbed into parent synthesis without a
partial,timed_out,blocked, orsupersededterminal state - Parallel work claimed as faster without naming saved uncertainty, duplicated work, and the future command/check/hot path it created
- A batch that closes with green Steward gates but no product delta, product-native gate, screenshot/perf proof, API behavior change, or user-facing workflow improvement while still claiming product acceleration
Subagent hints (Codex / Cursor / Zed)
- Use read-only agents for exploration and review
- Pass the handoff block verbatim in the subagent prompt
- Prefer
disable-model-invocation: trueon skills that must run only when invoked - For parallel work, keep agent scopes non-overlapping and declare write ownership before implementation.
- Useful reviewer roles include
Repo Truth Verifier,Boundary Leak Reviewer,Evidence Ladder Reviewer,Doc Collapse Reviewer,Harness QA Reviewer, andStale External Assumption Reviewer. - Codex custom agents live in
.codex/agents/*.tomlor~/.codex/agents/*.toml; definename,description, anddeveloper_instructions, and spawn subagents only when the user explicitly asks for subagent delegation. - Cursor custom subagents live in
.cursor/agents/*.mdor~/.cursor/agents/*.md; each run has isolated context, and background/parallel execution is useful for independent slices. - Zed parallel work uses separate agent threads or worktrees; use skills for repeatable single-context procedures and threads for independent concurrent work.
Install
npx skills add arenukvern/skill_steward --skill multi-agent-handoffSources
See references/sources.md. When researching, follow skill-source-citations.
© Arenukvern, 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 7 other files (references) in .agents/skills/multi-agent-handoff of Arenukvern/mcp_flutter.
- SKILL.md
- evals/cases/parallel-batch-contract-trigger.yaml
- evals/cases/parallel-overhead-collapse-trigger.yaml
- evals/cases/parallel-product-impact-guardrail-trigger.yaml
- evals/cases/temp-proof-landing-trigger.yaml
- references/evals.md
- references/handoff-template.md
- references/sources.md
Open the folder on GitHubat commit 62f3ee1
Compare with similar skills
Multi 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Multi Agent Handoff this skillArenukvern/mcp_flutter | 386 | — | ~2.7k | Automated safety check: Pass | MIT | |
| Orca CLIstablyai/orca | 88k | 2 repos | ~593 | Automated safety check: Pass | MIT | |
| Paseo Advisor Second Opiniongetpaseo/paseo | 20k | 1 repos | ~756 | Automated safety check: Pass | Custom licence | |
| O2 Review Loopopenobserve/openobserve | 22k | — | ~3.7k | Automated safety check: Pass | AGPL-3.0 | |
| Paseo Committeegetpaseo/paseo | 20k | 1 repos | ~496 | Automated safety check: Pass | Custom licence | |
| Mission Control Agent APIbuilderz-labs/mission-control | 6.3k | — | ~2.1k | Automated safety check: Pass | MIT |
Similar skills
Paseo Advisor Second Opinion
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.
O2 Review Loop
openobserve/openobserve
Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.
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.
Mission Control Agent API
builderz-labs/mission-control
Teaches an agent to use the Mission Control dashboard API: register, send heartbeats, fetch assigned tasks, report progress and disconnect, with API key auth.
Paseo Agent Handoff
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.
More from Arenukvern/mcp_flutter
All 23 skills in this repoHarness Engineering Lifecycle
Arenukvern/mcp_flutter
Design, implement, and integrate generalized validation harnesses across a producer-consumer boundary after a local harness contract exists.
Mixture Of Experts
Arenukvern/mcp_flutter
Run a Mixture of Experts (MoE) audit on any topic, plan, codebase, evidence archive, or process.
Plugin Marketplace Setup
Arenukvern/mcp_flutter
Designs public or private Agent Skill and plugin marketplaces for Cursor, Claude Code, Codex, Zed, Open Plugin, and npx skills—manifest layout, install matrix, and Skill Steward vs product boundaries.
Release Changelog Harness
Arenukvern/mcp_flutter
Chooses ecosystem-native release and changelog tooling (Changesets, Melos, release-plz) plus binary distribution (GitHub Release tarballs, install.sh) when the product is an executable.
Repository Governance Lifecycle
Arenukvern/mcp_flutter
Master orchestration for repository governance, North Star impact, sub-Star boundaries, and repair-first or evidence-first drift checks.
Skill Authoring Lifecycle
Arenukvern/mcp_flutter
Scaffold and formally review a new Agent Skill in this marketplace repo.
Related
Categories
Questions about Multi Agent Handoff
What does Multi Agent Handoff do?
Plan and document handoffs, parent lane contracts, and parallel batch contracts between specialized AI agents (foreman, workers, reviewers). Multi Agent Handoff is an agent skill from Arenukvern/mcp_flutter. Plan and document handoffs, parent lane contracts, and parallel batch contracts between specialized AI agents (foreman, workers, reviewers).
When should I use Multi Agent Handoff?
Multi Agent Handoff fits situations like: multi-agent workflows; original goal preservation; terminal states; guild-style agent coordination.
How do I install Multi Agent Handoff in Claude Code?
Run `npx skills add Arenukvern/mcp_flutter --skill multi-agent-handoff -a claude-code`. Or copy the skill folder (.agents/skills/multi-agent-handoff in Arenukvern/mcp_flutter) into .claude/skills/multi-agent-handoff in your project. Claude Code loads it when a task matches its description.
How do I install Multi Agent Handoff in Codex?
Run `npx skills add Arenukvern/mcp_flutter --skill multi-agent-handoff -a codex`. Or copy the skill folder (.agents/skills/multi-agent-handoff in Arenukvern/mcp_flutter) into .agents/skills/multi-agent-handoff in your project. Codex loads it when a task matches its description.
Can I use Multi 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 Arenukvern/mcp_flutter --skill multi-agent-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/multi-agent-handoff, .gemini/skills/multi-agent-handoff, .github/skills/multi-agent-handoff and .opencode/skills/multi-agent-handoff in your project.
What does Multi Agent Handoff need to run?
Going by SKILL.md and its folder, Multi Agent Handoff needs the command-line tools its instructions call (npx). Our summary lists: Node.js.
Does Multi Agent Handoff access the network?
SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Multi 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 Multi Agent Handoff use?
Multi Agent Handoff is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Multi Agent Handoff use?
About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.1k tokens, read only when the agent opens those files.
What are the alternatives to Multi Agent Handoff?
Skills that share tags, products or a category with Multi Agent Handoff: Orca CLI (stablyai/orca, 88k stars), Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars), O2 Review Loop (openobserve/openobserve, 22k stars) and Paseo Committee (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Multi Agent Handoff?
Arenukvern (a GitHub user) maintains it in Arenukvern/mcp_flutter, which has 386 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on October 3, 2026.
Source: Arenukvern/mcp_flutter on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.