human-in-the-loop

human-in-the-loop is a skill for Claude Code, Codex from hajekim/agentic-design-patterns-skills. It costs 412 tokens per session (3,622 once invoked), scanned A, original, MIT.

A pattern that pauses an agent at important checkpoints so a person can approve an action, answer a question, or provide feedback before the agent continues.

In plain words
What is it for?
Use it for approval steps before sending messages, deleting data, making financial transactions, giving sensitive advice, or handling uncertain situations.
Why use it?
It keeps people involved when actions are irreversible, high-risk, ambiguous, regulated, or affect other people.

Skill for Claude CodeCodex

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

Good fit Use it for approval steps before sending messages, deleting data, making financial transactions, giving sensitive advice, or handling uncertain situations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hajekim/agentic-design-patterns-skills/human-in-the-loop
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 hajekim/agentic-design-patterns-skills --skill human-in-the-loop
Clone the repo
git clone --depth 1 https://github.com/hajekim/agentic-design-patterns-skills

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-in-the-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-skills/human-in-the-loop/github.svg)](https://agentmods.dev/skills/hajekim/agentic-design-patterns-skills/human-in-the-loop)
Your own site
<a href="https://agentmods.dev/skills/hajekim/agentic-design-patterns-skills/human-in-the-loop"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-skills/human-in-the-loop/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 human-in-the-loop

Your own site · 80×15
<a href="https://agentmods.dev/skills/hajekim/agentic-design-patterns-skills/human-in-the-loop"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-skills/human-in-the-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 412 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,622 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 $0.00412 $0.03622
Opus 5 $0.00206 $0.01811
Sonnet 5 $0.00082 $0.00724
Haiku 4.5 $0.00041 $0.00362

Measured 10d ago against content hash f70bb91858dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

human-in-the-loop 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 10d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/human-in-the-loop/SKILL.md · 392 lines

How it starts

The opening of the file, as written. The whole thing — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Human-in-the-Loop (HITL) Pattern

Overview

The Human-in-the-Loop (HITL) Pattern integrates human judgment, oversight, and approval into agent workflows at critical decision points. Rather than running fully autonomously, HITL agents pause at defined checkpoints — to confirm high-stakes actions, request clarification, seek approval, or collect feedback — before proceeding.

Core Principle: Autonomy is earned, not assumed — build human oversight into the design, not as an afterthought.

When This Skill Applies

Activate this pattern when:

  • Agent actions are irreversible (sending emails, deleting data, financial transactions)
  • High-risk decisions require human judgment (medical, legal, financial advice)
  • Ambiguous instructions need human clarification before proceeding
  • Regulatory or compliance requirements mandate human approval
  • Agent confidence is below acceptable threshold for autonomous action
  • Actions affect third parties who have not consented to fully automated interaction
  • The agent encounters situations outside its training distribution

Rule of thumb: If you'd want a human to review the action before it happens, build in a HITL checkpoint.

HITL Spectrum

Fully Autonomous ←————————————————————→ Fully Manual
       |           |           |           |
   Auto-run    Approve     Review      Step-by-step
  (no review)  high-risk   all steps    approval

Choose the appropriate level based on:

  • Risk: Higher risk → more human involvement
  • Trust: Proven, well-tested agents can operate more autonomously
  • Context: Production vs. development, internal vs. external-facing
  • Reversibility: Irreversible actions need pre-approval

DEFINE → PLAN → ACTION Workflow

DEFINE

Map the human oversight requirements:

  1. Which actions are irreversible or high-risk?
  2. Which decision points require human judgment (not just execution)?
  3. What information does the human need to make an informed approval?
  4. What are the response time requirements? (Synchronous vs. async approval)
  5. What happens if the human is unavailable?

Read the full file on GitHub · 392 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. 10d ago First seen · 392 lines · 412 tokens per session scan A f70bb91858dc

Subscribe to this mod's changes

human-in-the-loop is a skill published in the GitHub repository hajekim/agentic-design-patterns-skills (4 stars, last pushed 5mo ago), licensed MIT. It adds 412 tokens to every session and 3,622 once invoked, about $0.0021 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.

Related

Other skills, from other repositories

impact-audit

Blast radius of a change you have not made yet -- traces a symbol across federated repositories, splits impact per repo, and reports what must ship together.

n24q02m/better-code-review-graph · 35 tokens

onboard-repo

Index an unfamiliar codebase into the knowledge graph, then produce a first orientation map -- entry points, most-depended-upon modules, hotspots, test topology.

n24q02m/better-code-review-graph · 38 tokens

prompt-optimizer

Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite…

Jamkris/everything-gemini-code · 179 tokens

openclaw-persona-forge

A persona-design guide for OpenClaw agents, including their identity, personality, boundaries, names, and avatar prompts. OpenClaw is the specific agent platform this guide targets.

Jamkris/everything-gemini-code · 221 tokens

gemini-api

Google Gemini API patterns for Python and TypeScript. Covers content generation, streaming, tool use (function calling), vision, system instructions, context caching, batch requests, and agent workflows. Use when building applications with the Gemini API or Google Generative AI SDKs.

Jamkris/everything-gemini-code · 57 tokens

jira-integration

Use this skill when retrieving Jira tickets, analyzing requirements, updating ticket status, adding comments, or transitioning issues. Provides Jira API patterns via MCP or direct REST calls.

Jamkris/everything-gemini-code · 37 tokens