human-in-loop-agents SKILL.md skillA
human-in-loop-agents from latestaiagents/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add latestaiagents/agent-skills/human-in-loop-agents@git:20260205.a0b8780Pins git:20260205.a0b8780 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- latestaiagents/agent-skills
- Path
plugins/agent-architect/skills/patterns/human-in-loop-agents/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260205.a0b8780, committed Feb 5, 2026
- Size
- 9,852 bytes
- Repository stars
- 6
- License
- MIT
Build agents that pause for human approval, review, and intervention. Use this skill when implementing approval workflows, human oversight, agent interrupts, or review-before-execute patterns. Activate when: human in the loop, HITL, agent approval, human oversight, interrupt agent, pause agent, review workflow, agent supervision.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Human-in-the-Loop Agents
**Build agents that know when to stop and ask for human judgment.**
## Why Human-in-the-Loop?
Critical for:
- **High-stakes actions**: Financial transactions, data deletion
- **Compliance**: Audit requirements, approval workflows
- **Quality control**: Review before publishing, sending
- **Edge cases**: When agent confidence is low
- **Trust building**: Users control what agents do
## Core Patterns
### Pattern 1: Interrupt Before Action
```python
from langgraph.graph import StateGraph, END
from langgraph.checkpoint.memory import MemorySaver
from langgraph.types import interrupt
class AgentState(TypedDict):
messages: list
pending_action: dict | None
approved: bool
def plan_action(state: AgentState) -> dict:
"""Agent plans what to do."""
# Determine action based on messages
action = {
"type": "send_email",
"to": "user@example.com",
"subject": "Important Update",
"body": "..."
}
return {"pending_action": action, "approved": False}
def request_approval(state: AgentState) -> dict:
"""Interrupt and wait for human approval."""
action = state["pending_action"]
…Read the whole file at its exact version.
How to install
mdr add latestaiagents/agent-skills/human-in-loop-agents@sha256:756de5d96fe08fd5The line at the top of this page pins the label git:20260205.a0b8780, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_jzcganqq4y2sbcke)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Feb 5, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (9852 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
latestaiagents/agent-skills · 6 stars · license MIT · pushed 2026-11-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_jzcganqq4y2sbcke GET https://markdownregistry.com/api/v1/resolve?ref=latestaiagents/agent-skills/human-in-loop-agents GET https://markdownregistry.com/api/v1/blob/756de5d96fe08fd50b211d5a9c80d716c34dc2ed9862aac79056a0be8b059cdc
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.