agentmods.dev

human-handoff

human-handoff is a skill for Claude Code, Codex from Akakaui/visual-browser-agent. It costs 26 tokens per session (849 once invoked), scanned A, original, MIT.

A human handoff workflow for situations an automated agent should not handle alone, such as login, CAPTCHA, two-factor authentication, payments, public submissions, deletion, or unclear choices.

In plain words
What is it for?
Use it to request help with authentication challenges, review OAuth consent, approve external changes, complete CAPTCHA or 2FA, and resolve ambiguity.
Why use it?
It keeps sensitive or irreversible actions under human control and provides a way to resume after the person completes or approves the required step.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 0repo 13d ago A scan 26 tokens original MIT

Good fit Use it to request help with authentication challenges, review OAuth consent, approve external changes, complete CAPTCHA or 2FA, and resolve ambiguity.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/akakaui/visual-browser-agent/human-handoff
View source ↗ Akakaui/visual-browser-agent
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 Akakaui/visual-browser-agent --skill human-handoff
Clone the repo
git clone --depth 1 https://github.com/Akakaui/visual-browser-agent

Made for: Claude Code, Codex.

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 human-handoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/akakaui/visual-browser-agent/human-handoff.svg)](https://agentmods.dev/skills/akakaui/visual-browser-agent/human-handoff)
Your own site
<a href="https://agentmods.dev/skills/akakaui/visual-browser-agent/human-handoff"><img src="https://agentmods.dev/badge/skills/akakaui/visual-browser-agent/human-handoff.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 849 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.00849
Opus 5 $0.00013 $0.00425
Sonnet 5 $0.00005 $0.00170
Haiku 4.5 $0.00003 $0.00085

Measured 6d ago against content hash 305cd8d238d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

human-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.

skills/human-handoff/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Human Handoff Skill

When to Use

Use this skill when the agent encounters situations requiring human intervention:

  • Login/authentication flows
  • CAPTCHA challenges
  • Two-factor authentication (2FA)
  • OAuth consent screens
  • Payment flows
  • Account settings changes
  • Public submissions (posts, messages, purchases)
  • Destructive actions (deletion, irreversible changes)
  • Unresolved ambiguity after evidence review

Instructions

Authentication Flows

  1. Detect login page via inspect_page (look for password fields, OAuth buttons)
  2. Call ask_human with sensitive: true and form schema for credentials
  3. Use request_approval for OAuth consent
  4. Wait for human to complete in browser takeover view
  5. Resume with navigate or inspect_page to verify success

CAPTCHA/2FA

  1. Detect challenge via page inspection
  2. Call ask_human with sensitive: true, screenshot, and clear instructions
  3. Provide open_takeover_view for direct browser access
  4. Wait for resume signal

Sensitive Actions

  1. Before any public submission, purchase, or deletion:
    • Call request_approval with action details
    • Show screenshot of current state
    • Wait for explicit approval
  2. Use submit_public_action only after approval
  3. Capture evidence before and after

Ambiguity Resolution

  1. When evidence review yields low confidence:
    • Call ask_human with options
    • Provide relevant screenshots/clips
    • Let human decide next step

Decision Flow

Page requires auth?
  → ask_human (sensitive: true) → human completes → resume
  
Page has CAPTCHA/2FA?
  → ask_human (sensitive: true) + open_takeover_view → human completes → resume
  
Action is public submission/purchase/deletion?
  → request_approval → if approved → submit_public_action
  
Evidence review confidence < 0.7?
  → ask_human with options → human decides → continue

Safety

  • NEVER request passwords/tokens via form mode (use URL mode / browser takeover)
  • Always capture screenshot before and after sensitive actions
  • Log all human interactions for audit
  • Respect human.requireFor config list
  • Require human.requireResumeButton for takeover flows

Read the full file on GitHub · 111 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 · 111 lines · 26 tokens per session scan A 305cd8d238d1

Subscribe to this mod's changes

human-handoff is a skill published in the GitHub repository Akakaui/visual-browser-agent (0 stars, last pushed 13d ago), licensed MIT. It adds 26 tokens to every session and 849 once invoked, about $0.0001 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 2026-08-31.

Building agents
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens