A handoff workflow for finishing a local web-app session and preparing it for engineering. It creates a task list, checks that changes stay frontend-only, requires Storybook examples for changed components, and coordinates linting, type checks, tests, and review through other agents.

Use it to prepare a browser-based prototype for engineering, verify its frontend scope, record remaining tasks, and run the stated quality checks.

It turns an informal prototype into a documented starting point for engineers without asking the original user to understand the engineering process. It also exposes issues before the work is handed over.

handoff — Skill for Claude Code and Codex by closedloop-ai

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 closedloop-ai/claude-plugins --skill handoff

Clone the repo

git clone --depth 1 https://github.com/closedloop-ai/claude-plugins

Made for: Claude Code, Codex.

Or install vibe, the plugin that ships this one along with the rest of its 10 skills, 16 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/handoff/github.svg)](https://agentmods.dev/skills/closedloop-ai/claude-plugins/handoff)

Your own site

<a href="https://agentmods.dev/skills/closedloop-ai/claude-plugins/handoff"><img src="https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/closedloop-ai/claude-plugins/handoff"><img src="https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 144 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,252 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00144	$0.06252
Opus 5.5	$0.00058	$0.02501
Sonnet 5.5	$0.00029	$0.01250
Haiku 4.5	$0.00014	$0.00625

Measured today against content hash a6f4fc23fee5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 today.

The scan reads SKILL.md. This mod also ships 10 executable files (scripts/allowlist-shrink.mjs, scripts/allowlist-shrink.test.mjs, scripts/handoff-inventory.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/vibe/skills/handoff/SKILL.md · 476 lines

How it starts

The opening of the file, as written. The whole thing — 476 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Handoff

The person ran vibe and built something they are happy with. You orchestrate making it safe and complete for the next people, without asking them to understand any of the engineering. The session's live ClosedLoop ticket was created when the session started and the workers kept it current; handoff checks it is complete rather than writing it. The person says who picks the work up next, and the ticket is assigned to them. Usually that is design, who reviews the components in the branch's Vercel Storybook and comments on the ticket on sign-off, then engineering, who finishes the work through analysis, a pull request, and merge; sometimes it goes straight to engineering. The ticket stays In Progress throughout, and no pull request is opened here.

Your role: orchestrate, never do the work

The same rule as the vibe skill, without exception: you never read source files, search the codebase, edit files, read diffs or tickets in full, or run builds, tests, linters, reviews, git, or gh yourself. You keep an internal checklist, talk to the person, run this skill's inventory script, the vibe session script, and the vibe commit script (short JSON), and dispatch workers. You commit, through ../vibe/scripts/commit-worktree.mjs; no worker ever commits, because a commit runs the repository's commit hooks. Each worker returns a short status (DONE, NEEDS_PERSON, NEEDS_REVIEW, BLOCKED). Apply ../vibe/references/quality-loop.md before relaying any question: research product decisions first and ask only an absolutely necessary unresolved one, never a technical question. Route the answer as "Answers from the person" below says. Updates mention only completed features and next work; planning, reviews and the checklist stay internal. Every worker brief says closedloop-graph is required (../vibe/references/closedloop-graph.md): each worker that locates, changes, or reviews code makes its required calls and ends its result with a Graph block. A result without one, or with one that lists no calls, is incomplete; dispatch the worker again saying so. A Graph block that says unreachable keeps that step moving; dispatch vibe-setup-worker to restore the connection before the next step. Every worker that edits the live ticket follows ../vibe/references/ticket-template.md.

Read the full file on GitHub · 476 lines

Files

What ships with it

11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

today Changed · +128 lines a6f4fc23fee5
yesterday Changed · -1 lines · -91 tokens per session 1674d188b557
2d ago Changed · +131 lines · +23 tokens per session aec175c51e65
3d ago Changed · +13 lines db964be1304d
4d ago First seen · 205 lines · 212 tokens per session scan A 6dc71e0fd5e0

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository closedloop-ai/claude-plugins (122 stars, last pushed today), licensed Apache-2.0. It adds 144 tokens to every session and 6,252 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-06.

Claude Code Frontend LLM Testing agentic-ai ai-agents anthropic developer-tools

ci-speedup

Cuts the wait from push to green by measuring a pipeline's critical path from run timestamps, then splitting, sharding, trimming setup and sharing test module state, with a before/after ledger. Use when asked to "speed up CI", "CI is slow", "why does a PR take 15 minutes", "CI is the bottleneck", or when agents merge…

mblode/agent-skills · 83 tokens

app-verification

Builds and maintains a repo's own verification harness (verify CLI, doctor, worktree isolation, feature map, seed data) and a reproduce-first bug handoff. Use when asked to "build a verification harness", "add a doctor command", "prove every feature still works", or "reproduce this bug report".

mblode/agent-skills · 69 tokens

audit-harness

Use when auditing HARNESS.md, pre-commit hooks, pre-push hooks, architecture gates, or CI workflows for tunacode-cli. This skill treats any mismatch, skipped gate, or failing check as a critical failure and requires manual one-by-one execution rather than make targets, batch wrappers, or summary-only audits.

alchemiststudiosDOTai/tunacode · 69 tokens

auto-optimize

Autonomously optimize an existing skill's output quality by running it repeatedly, scoring against binary evals, mutating the prompt, and keeping improvements. Started only by the user, because it edits the skill in place and runs many paid model calls.

LeeJuOh/claude-code-zero · 54 tokens

test-audit

Prunes low-value tests across a whole suite to a measured target while holding coverage. Use when asked to "remove useless tests", "prune the test suite", "we have too many tests", "agents keep writing pointless tests", or "cut 20% of tests without losing coverage".

mblode/agent-skills · 63 tokens

mcp-tool-developer

Build Model Context Protocol (MCP) servers and tools from scratch. Full-stack MCP development with TypeScript/Python, testing, deployment, and registry publishing.

LiHongwei-cn/lihongwei-cn · 38 tokens