swarm-handoff

swarm-handoff is a skill for Claude Code from ulises-jeremias/agent-toolkit. It costs 30 tokens per session (1,167 once invoked), scanned A, original, MIT.

A handoff workflow for moving files or commits between roles in a multi-agent coding team. Each writer works in a separate Git branch and worktree, an isolated copy of the files.

In plain words
What is it for?
Use it to prepare implementation context, pass artifacts from implementers to reviewers or integrators, and promote committed work through the workflow.
Why use it?
It keeps handoffs traceable and prevents agents from overwriting one another's changes or relying on copied chat messages.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the agent-toolkit-complete plugin — 116 skills shipped together

Good fit Use it to prepare implementation context, pass artifacts from implementers to reviewers or integrators, and promote committed work through the workflow.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ulises-jeremias/agent-toolkit/swarm-handoff
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ulises-jeremias/agent-toolkit --skill swarm-handoff
Clone the repo
git clone --depth 1 https://github.com/ulises-jeremias/agent-toolkit

Made for: Claude Code.

Or install agent-toolkit-complete, the plugin that ships this one along with the rest of its 116 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for swarm-handoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/swarm-handoff/github.svg)](https://agentmods.dev/skills/ulises-jeremias/agent-toolkit/swarm-handoff)
Your own site
<a href="https://agentmods.dev/skills/ulises-jeremias/agent-toolkit/swarm-handoff"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/swarm-handoff/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for swarm-handoff

Your own site · 80×15
<a href="https://agentmods.dev/skills/ulises-jeremias/agent-toolkit/swarm-handoff"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/swarm-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,167 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.01167
Opus 5 $0.00015 $0.00583
Sonnet 5 $0.00006 $0.00233
Haiku 4.5 $0.00003 $0.00117

Measured 6d ago against content hash 970cefce234c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

swarm-handoff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/agent-toolkit-complete/.github/skills/swarm-handoff/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Swarm Handoff

Create correct file handoffs between swarm roles so work moves via Git + filesystem, not chat copy. Every writer gets an isolated worktree/branch; the filesystem state.json is authoritative.

When to use

  • The swarm needs to move work: implementer → reviewer → integrator (or any from -> to).
  • User asks to "hand off", "delegate", "send artifact", or "promote".
  • After swarm-observer diagnoses a stuck active handoff.

Prerequisites

  • Run exists: .agent-toolkit/swarm/runs/<run-id>/state.json.
  • Artifact file lives under the repo (prefer artifacts/). For commit type, commit/branch must exist locally.
  • Know from and to roles from the recipe (pair: implementer→reviewer; team: implementer→reviewer→integrator).

Workflow

1. Prepare the artifact (file handoff is preferred)

# Artifact — by convention in artifacts/
mkdir -p artifacts
cat > artifacts/<name>.md <<'EOF'
# Context for <to>
- What was implemented and why
- Files changed and how to verify
- Risks / open questions
EOF
git add artifacts/<name>.md  # optional, but keeps history

# Commit handoff — use when work is already committed
git log --oneline -n 5
git branch --show-current

2. Create the handoff (CLI owns state)

# Artifact handoff — triggers auto-provision of <to>'s worktree/tab + agent
agent-toolkit swarm handoff create --type artifact --from implementer --to reviewer --artifact artifacts/cna-ideas.md --run-id <run-id>

# Commit handoff
agent-toolkit swarm handoff create --type commit --from reviewer --to integrator --commit <sha> --branch <branch> --run-id <run-id>

# Auto behavior:
# - If an active handoff exists where to == from_role, it auto-completes (auto:true) and trace records handoff_completed.
# - Next role gets eager window (Waiting for handoff: <from> -> <to>) replaced by real prompt: export AGENT_TOOLKIT_SWARM_RUN_ID/RUN_DIR/REPO SWARMFORGE_ROLE + cd worktree && exec <runner> "$(cat prompt)"

Verify:

agent-toolkit swarm handoffs --run-id <run-id> --json | jq '.[] | {id,from,to,status,artifact,commit,auto}'
agent-toolkit swarm status --run-id <run-id> --json | jq '.trace | last'
# Expect: handoff create logs, worktree path, and runner exec with $(cat prompt)

Read the full file on GitHub · 113 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 113 lines · 30 tokens per session scan A 970cefce234c

Subscribe to this mod's changes

swarm-handoff is a skill published in the GitHub repository ulises-jeremias/agent-toolkit (16 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 1,167 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.

Related

Other skills, from other repositories

github-navigator

GitHub operations via gh CLI. CRITICAL: Use instead of WebFetch for any github.com URL or GitHub repo path like owner/repo. Use when the user asks to inspect repositories, files, issues, pull requests, releases, Actions runs, or repository structure. Use when the user says 'show README', 'list issues', 'check PR'…

arvindand/agent-skills · 107 tokens

active-review

Use when the user wants to prepare for a manual PR code review and asks for help targeting it — a terse PR summary, ranked files to read first, and paste-ready inline comment drafts with GitHub deep-links. Triggers: "active review this PR", "walk me through this PR", "help me review this", "give me inline comments to…

paultyng/skill-issue · 157 tokens

analyze-knowledge

Use when the user asks who knows specific code, who should review a PR or files, what the lottery factor is, whether knowledge is concentrated or spread, who to talk to about a code area, or when suggesting reviewers beyond GitHub's built-in suggestions.

paultyng/skill-issue · 57 tokens

bisect

Use when hunting a regression, phrases like "bisect", "find the commit that broke X", "this used to work", "regression in test Y", "when did start". Also use when escalated from ci-debug-loop because log analysis can't pinpoint the offending change, or when a previously-passing test/build/behavior is now failing and…

paultyng/skill-issue · 121 tokens

fix-pr-conflict

Resolve merge conflicts on a pull request by rebasing onto the base branch. Use when a PR is not mergeable, has merge conflicts, or the user asks to fix conflicts on a PR.

paultyng/skill-issue · 44 tokens

ship-it

End-to-end shipping workflow. Formats, lints, tests, creates a changelog entry, commits with conventional commits, pushes, updates PR description, and suggests reviewers. Use when the user says "ship it", "commit and push", "fmt lint test commit push", or similar shipping commands.

paultyng/skill-issue · 63 tokens