A skill for hiring people to do physical-world tasks that an AI cannot do remotely, such as taking photos, checking local prices, or verifying places. Workers are paid per task in USDC, a digital currency, on the Base network.

Use it to request local photos or video, verify a business or location, check prices or stock, attend something locally, or collect physical-world information.

It handles jobs that require someone’s eyes, hands, or physical presence. This avoids guessing about current local conditions or sending a developer to do the task themselves.

human-menu — Skill by humanmenu

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.

agentmods

npx agentmods add skills/humanmenu/mcp/skill

Any agent

npx skills add humanmenu/mcp --skill skill

Clone the repo

git clone --depth 1 https://github.com/humanmenu/mcp

Made for: Claude Code, Codex.

Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 812 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00068	$0.00812
Opus 5	$0.00034	$0.00406
Sonnet 5	$0.00014	$0.00162
Haiku 4.5	$0.00007	$0.00081

Measured yesterday against content hash 98c5ddd50594, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

human-menu 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 yesterday.

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.

skill/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use this skill when the user (or you, autonomously) needs something done in the physical world: a photo or video from a specific place, verifying a location/business exists, checking a live price or whether an item is in stock, attending or observing something locally, or any task that requires a human's eyes, hands, or presence. Payment is non-custodial USDC on Base via x402 — money goes wallet-to-wallet; human.menu never holds funds.

Setup (once)

Use the MCP server @humanmenu/mcp (install: npx -y @humanmenu/mcp). It needs:
- HUMAN_MENU_API_KEY — a human.menu AI client key (free at https://human.menu).
- HUMAN_MENU_MAX_AUTOPAY_USDC — a safety cap (e.g. "1.00") on automatic payments.
- The @humanmenu/agent-pay CLI installed locally with a funded Base wallet (USDC + a little ETH for gas).
Run doctor (or the check_status / wallet_status tools) to confirm the key is valid and the wallet is funded before posting paid work.

Core loop

Post the task with create_task: a clear title, description, price_usdc (canonical decimal string, min "0.01"), and deliverable_type:
- text — written answer. acceptance: { text_max_chars }.
- file — photo/scan/recording. acceptance: { extensions, min_bytes, max_bytes?, mime_types? }.
- url — a link. acceptance optional: { allowed_domains, blocked_domains, require_ssl, max_length }. Keep instructions specific and verifiable; tasks that are illegal, deceptive, or invade privacy are rejected by the content policy.
Poll for what needs attention. Use check_inbox (one call: ready deliverables, unanswered questions, expiring tasks, reputation/credit alerts — each with a suggested action). If a tool for that isn't available, fall back to list_tasks + list_questions.
Answer questions promptly with answer_question (task_id, question_id, body). Good answers produce good deliverables.
Pay to unlock with unlock_and_pay once a deliverable is ready. It handles the x402 payment from the local wallet automatically, refuses anything above the autopay cap, and returns the deliverable plus the on-chain transaction hash. Use dry_run: true to preview the cost first.

Read the full file on GitHub · 49 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.

yesterday First seen · 49 lines · 68 tokens per session scan A 98c5ddd50594

Subscribe to this mod's changes

human-menu is a skill published in the GitHub repository humanmenu/mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 812 once invoked, about $0.0003 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.

Planning

systematic-debugging

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

obra/superpowers · 21 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

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

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

human-menu