humanasllm: Skill for Claude Code

.claude/skills/dispatch-human/SKILL.md

dispatch-human is a skill for Claude Code from leenkcool/humanasllm. It costs 83 tokens per session (1,304 once invoked), scanned A, original, MIT.

A handoff process for sending sensitive, private, or human judgment tasks to a human engineer. It records the request and later checks whether the engineer has delivered a result.

In plain words
What is it for?
Delegating confidential work, tasks requiring human decisions, project-required human implementation, or work needing extra access or external resources.
Why use it?
It keeps tasks that should not go to a public AI model, or that require a person, in a separate human review process.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is leenkcool/humanasllm's own configuration. It tells Claude Code how to work on humanasllm itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything humanasllm configures →

Reuse

Borrowing it

Nothing to install: this file belongs to leenkcool/humanasllm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/leenkcool/humanasllm/main/.claude/skills/dispatch-human/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/leenkcool/humanasllm

Made for: Claude Code.

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 dispatch-human

README.md
[![agentmods](https://agentmods.dev/badge/skills/leenkcool/humanasllm/dispatch-human/github.svg)](https://agentmods.dev/skills/leenkcool/humanasllm/dispatch-human)
Your own site
<a href="https://agentmods.dev/skills/leenkcool/humanasllm/dispatch-human"><img src="https://agentmods.dev/badge/skills/leenkcool/humanasllm/dispatch-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.

agentmods 80×15 button for dispatch-human

Your own site · 80×15
<a href="https://agentmods.dev/skills/leenkcool/humanasllm/dispatch-human"><img src="https://agentmods.dev/badge/skills/leenkcool/humanasllm/dispatch-human.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,304 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 $0.00083 $0.01304
Opus 5.5 $0.00033 $0.00522
Sonnet 5.5 $0.00017 $0.00261
Haiku 4.5 $0.00008 $0.00130

Measured 2mo ago against content hash f6e57cd8d266, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dispatch-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 2mo 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.

.claude/skills/dispatch-human/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

派单给人工工程师(dispatch-human)

本 Skill 是「humanllm agent」的触发入口:它自己不实现任务,而是整理触发条件 → 委派给 humanllm agent → 回传人工产出。

Trigger(何时触发)

  • 用户明确要求人工处理:「交给人工」「派给人类」「让工程师做」「需要真人实现」
  • 任务涉密 / 私有内部逻辑 / 不可外传 / 敏感业务
  • 项目规则(CLAUDE.md)明确要求人工编写
  • 任务可能额外需要外部资源(服务器 / API Key / 权限 / 环境)——humanllm 会自动先提审批

Steps(主代理执行)

  1. 读取 调用者任务原文与全部上下文(messages、约束、涉密标记)。
  2. 标注交人工原因:安全原因 或 项目规则要求,随任务一并传给 agent。
  3. 委派:调用 Agent 工具,参数如下:
    subagent_type: "humanllm"
    prompt: <任务原文 + 交人工原因标注>
    run_in_background: false      // /v1 异步受理,humanllm 登记未完成、之后回查交付;大任务可后台
    
    humanllm 会按 .claude/agents/humanllm.md 自动把任务整理成「完整上下文包」(【任务】【交人工原因】【项目与代码库】【接单流程】【环境约定】【要求】),写入 data/human_task.json 并提交 p390 网关。
  4. 登记未完成(humanllm 执行):/v1 异步受理立即返回 task_id(人工小时级,不再挂起等待)。humanllm 把 task_id 登记到 data/human_followup.json(pending)。
  5. 回查交付(humanllm 执行):后续做相关工作再次调用时,humanllm 先回查 GET /v1/tasks/:id——completed 把人工产出逐字返回(保留代码块与换行);未完成则如实反馈状态、保留登记继续轮候。

主代理只负责「判断触发 → 委派 → 接收产出/状态」,不直接读写 data/ 下任何文件;登记、回查、交付全部由 humanllm 按 .claude/agents/humanllm.md 自动完成。

跟进时机(何时再次委派 humanllm 回查)

humanllm 每次被委派都会先回查 data/human_followup.json 里的未完成任务。因此:

  • 用户再次提问、做与之相关的工作、或派新任务时,主代理先委派一次 humanllm(prompt 注明「先回查未完成的人工任务,再处理本次请求」),humanllm 会先交付已完成的产出、反馈未完成的状态,再继续本次工作。
  • 只要对话仍在进行,就把「跟进人工任务」作为相关工作开始前的固定动作,防遗忘。

委派参数速查

参数 值 说明
subagent_type humanllm 指定人工代理 agent
run_in_background false 异步受理:humanllm 登记未完成、跟进时回查交付;大任务可后台 true
model 省略 humanllm 定义已定(转发器,仅 haiku 占位)
isolation 省略 无需 worktree(转发类任务)

Verification(怎么算做对)

  • ✅ 确实调用了 humanllm agent(而非自行实现任务)。
  • ✅ 任务包六要素齐全(humanllm 保证):【任务】【交人工原因】【项目与代码库】【接单流程】【环境约定】【要求】。
  • ✅ 拿到 task_id 已登记到 data/human_followup.json(未完成,防遗忘)。
  • ✅ 回传内容是人工产出原文(completed 回查),未自行改写、未丢代码块/换行。
  • ✅ 未完成任务如实反馈状态(pending/processing/returned),未谎称完成,继续轮候。
  • ✅ 附上了任务编号(如 #21)与工作台地址 http://192.168.168.3:39000/login.html。

硬绑定变体(可选)

若希望整个 skill 直接以 humanllm agent 身份运行(跳过"主代理→委派"),把 frontmatter 改为:

Read the full file on GitHub · 75 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. 2mo ago First seen · 75 lines · 83 tokens per session scan A f6e57cd8d266

Subscribe to this mod's changes

dispatch-human is a skill published in the GitHub repository leenkcool/humanasllm (29 stars, last pushed 7d ago), licensed MIT. It adds 83 tokens to every session and 1,304 once invoked, about $0.0003 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 2026-08-30.

Related

dispatch-human compared with skills from other repositories

dispatch-human next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dispatch-humanleenkcool/humanasllmSkill297d agoMITA83Claude Code
browser-usebrowser-use/browser-useSkill120kyesterdayMITA57Claude Code, Codex
open-sourcebrowser-use/browser-useSkill120kyesterdayMITA137Claude Code
crit-storytomasz-tomczyk/critSkill1.3k2d agoMITA47Claude Code, Codex
snipedouard-claude/snipSkill478yesterdayMITA0Claude Code, Codex
goaizendev-sh/goaiSkill2346d agoMITA0Claude Code, Codex
generate-rfcsnurettincoban/ai-prd-workflowSkill30929d agoMITA34Claude Code