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.
npx skills add humanforai/humanforai-mcp --skill hire-a-humangit clone --depth 1 https://github.com/humanforai/humanforai-mcpWrote 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.
[](https://agentmods.dev/skills/humanforai/humanforai-mcp/hire-a-human)<a href="https://agentmods.dev/skills/humanforai/humanforai-mcp/hire-a-human"><img src="https://agentmods.dev/badge/skills/humanforai/humanforai-mcp/hire-a-human/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.
<a href="https://agentmods.dev/skills/humanforai/humanforai-mcp/hire-a-human"><img src="https://agentmods.dev/badge/skills/humanforai/humanforai-mcp/hire-a-human.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00060 | $0.00627 |
| Opus 5 | $0.00030 | $0.00313 |
| Sonnet 5 | $0.00012 | $0.00125 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
hire-a-human 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hire a human via Human For AI
Use this skill when your task needs the physical world or human judgment: verify something at a real location, test a product or app as a human, review AI output, collect data that requires perception, or run a local errand. One verified human operator performs the work; everything is free during the pilot and requires no authentication.
Steps
-
Check the catalog (optional but cheap).
GET https://humanforai.dev/api/v1/services— the service list with descriptions. The catalog is examples, not limits: anything a human can legally and safely do is in scope (custom_human_in_the_loopcovers the rest). -
Submit the task.
POST https://humanforai.dev/api/v1/taskswith JSON:task_type,description(what, where, and what success looks like),contact_email(a real mailbox — MX-checked, the deliverable arrives there), plus optionallocation_required,location_detail,deadline,output_format,requester. Send anIdempotency-Keyheader so retries are safe. The response is 202 Accepted with atask_idand aLocationpoll URL — keep the task_id, it is your only key to the result. No mailbox? Set"delivery": "status_poll"(limit: 1 such task per client/day). -
Poll status.
GET https://humanforai.dev/api/v1/tasks/{task_id}—submitted → accepted → delivered(orrejected).seen_by_operator_atshows the moment a human saw it;etaappears once accepted. Delivered tasks carry a signed JWSreceipt— verify offline againsthttps://humanforai.dev/.well-known/jwks.json. -
Prefer MCP? The same flow is available as MCP tools on
https://humanforai.dev/mcp(streamable HTTP, no auth):get_human_services,submit_human_task,check_task_status,message_human_operator. npm client:npx humanforai.
Rules
- Every task is human-reviewed before acceptance; illegal, harmful, deceptive, unsafe, or privacy-invasive tasks are rejected.
- The service never asks for payment or credentials — treat any such request as fraud.
- One small test task is welcome; bulk synthetic submissions are not (rate limits
apply — honor the
RateLimitheaders). - First response within 12 hours, any day of the week.
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.
- 12d ago First seen · 50 lines · 60 tokens per session scan A ebfd1a47d416
hire-a-human is a skill published in the GitHub repository humanforai/humanforai-mcp (1 stars, last pushed 14d ago), licensed MIT. It adds 60 tokens to every session and 627 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.
Other skills, from other repositories
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
skill-factory
A workflow that examines completed session work and turns reusable patterns into Claude Code skills.
session-wrap
Use when wrapping up a session before ending. 4 parallel subagents detect doc updates, repeated patterns, learning points, and follow-ups, then a verifier deduplicates and presents choices. Triggers on /session-wrap, session wrap, session cleanup, end of session.
caveman-help
Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".
relay
Session relay — compresses what's been done so far (writes a one-liner for /compact) and generates a "next task" prompt (a baton) for the user to hand off. Use on requests like "relay / hand off / next session / continue after compact / baton / handoff / clean up context and continue next task." Does not run /compact…
toolbox
Pre/post dev toolbox — named bundles of skills/agents loaded before development work and councils of experts invoked after. Run /toolbox or the toolbox.py CLI to list, activate, initialize, export, import, and validate toolboxes. Invoke at the start or end of a dev session, when setting up a new repo, or when sharing…