Home / mvschwarz / openrig · packages/daemon/specs/agents/shared/skills/core/human-in-the-loop/SKILL.md · GitHub

human-in-the-loop skillA

human-in-the-loop is agent-read markdown (skill) from mvschwarz/openrig: Use when classifying a slice closeout (auto-continue / human gate / park), routing a real decision to a human, or designing a human queue/dashboard surface. Treats humans as durable network participants with attention surfaces, queues, and decision records — escalation lands as a durable attention item, not a chat message. Approval is NOT required for every clean closeout; the default RSI conveyor continues unless an explicit human gate is reached..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Human In The Loop

The primitive that treats humans as **durable network participants** —
attention surfaces, queues, decision records, routing semantics — not
as ad-hoc chat receivers.

**Autonomy is not the absence of humans; it is knowing when human
judgment is needed and making that handoff crisp.**

## Use this when

- A slice closeout needs classifying: auto-continue, human gate, or park
- A real decision needs to land in front of a human (usage limits, provider auth, roadmap tradeoff, product-intent ambiguity)
- Designing a human queue/dashboard surface
- Returning a hot potato to orchestration after human approval

## Don't use this when

- The slice closeout is clean and `PROGRESS.md` already names the next safe slice. **Default RSI conveyor continues; do NOT manufacture a human gate.**
- The escalation is just a status update. Humans are participants for *decisions*, not narration.
- The next owner is another agent. Use queue-handoff, not human-in-the-loop.

## The 3-class closeout classification

In a productized daemon-backed version, closeout classifies the next
step BEFORE touching the human queue:

| Class | When | Action |
|---|---|---|
…

Read the whole file at its exact version.

How to install

Latest version
mdr add mvschwarz/openrig/human-in-the-loop@git:20260826.bdc404f
Exact content
mdr add mvschwarz/openrig/human-in-the-loop@sha256:14cf0c4a0dc89179

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ghqhmbqdev5v2zne.svg)](https://markdownregistry.com/a/art_ghqhmbqdev5v2zne)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260826.bdc404f latest2026-08-26 bdc404f 5,255 BA view · diff
git:20260802.4c6d8882026-08-02 4c6d888 5,263 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5255 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

GitHub

mvschwarz/openrig · 362 stars · license Apache-2.0 · pushed 2026-09-25 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ghqhmbqdev5v2zne
GET https://markdownregistry.com/api/v1/resolve?ref=mvschwarz/openrig/human-in-the-loop
GET https://markdownregistry.com/api/v1/blob/14cf0c4a0dc89179121465d4b8d81d40406427351adcdc34f875097d1e6e9ab2

Your agent 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.

More from mvschwarz/openrig

DESIGN.md@docs design
mvschwarz/openrig · docs/DESIGN.md
git:20260511.2c2e6ba · audit A · 362 stars
agent-operated-software skill
mvschwarz/openrig · packages/daemon/assets/plugins/openrig-core/skills/agent-operated-software/SKILL.md · Use when designing, building, operating, or diagnosing an ongoing application whose live backend or control loop…
git:20260908.e4e15c6 · audit A · 362 stars
agent-operated-workflows skill
mvschwarz/openrig · packages/daemon/assets/plugins/openrig-core/skills/agent-operated-workflows/SKILL.md · Use when a bounded real-world procedure has a deterministic happy path but brownfield, variable, or partially knowable…
git:20260907.9006fc5 · audit A · 362 stars
applying-a-permission-policy skill
mvschwarz/openrig · packages/daemon/assets/plugins/openrig-core/skills/applying-a-permission-policy/SKILL.md · Use when a user asks an agent to configure OpenRig command permissions, reduce repeated native approval prompts, or…
git:20260925.efde04f · audit A · 362 stars
claude-compaction-restore skill
mvschwarz/openrig · packages/daemon/assets/plugins/openrig-core/skills/claude-compaction-restore/SKILL.md · Use when a Claude Code session has just compacted, is about to compact, reached context limit, resumed after /compact…
git:20260907.3949b26 · audit A · 362 stars
delegating-work skill
mvschwarz/openrig · packages/daemon/assets/plugins/openrig-core/skills/delegating-work/SKILL.md · Use when you have a task and must decide WHO does it — yourself, a spawned subagent, or another agent in the topology…
git:20260805.864cea6 · audit A · 362 stars
forming-an-openrig-mental-model skill
mvschwarz/openrig · packages/daemon/assets/plugins/openrig-core/skills/forming-an-openrig-mental-model/SKILL.md · Use when the system around you does not make sense yet: you just booted into a seat and do not know how the pieces fit…
git:20260907.9006fc5 · audit A · 362 stars
loading-addressable-markdown skill
mvschwarz/openrig · packages/daemon/assets/plugins/openrig-core/skills/loading-addressable-markdown/SKILL.md · Use when a mission, slice, dashboard, or task references Markdown as path#h2-slug or path#h2-slug/h3-slug outside the…
git:20260901.0b86028 · audit A · 362 stars
messaging-the-human skill
mvschwarz/openrig · packages/daemon/assets/plugins/openrig-core/skills/messaging-the-human/SKILL.md · Use when project policy calls for a human decision or update, a human delivery is pending or failed, or a reply must…
git:20260910.0df014e · audit A · 362 stars
mission-slice-sop skill
mvschwarz/openrig · packages/daemon/assets/plugins/openrig-core/skills/mission-slice-sop/SKILL.md · Use when starting, building, handing off, restoring, or closing a mission or slice under the default lightweight SDLC.
git:20260906.ac21bc2 · audit A · 362 stars
openrig-operating-model skill
mvschwarz/openrig · packages/daemon/assets/plugins/openrig-core/skills/openrig-operating-model/SKILL.md · Use when you do not know WHERE something belongs: you learned a lesson and are unsure which file takes it; you are…
git:20260908.e4e15c6 · audit A · 362 stars
openrig-skills skill
mvschwarz/openrig · packages/daemon/assets/plugins/openrig-core/skills/openrig-skills/SKILL.md · Use when you're operating OpenRig and need the right skill or context for fleet recovery, seat handover, new-seat…
git:20260925.4940c10 · audit A · 362 stars

Every file in mvschwarz/openrig

Other files named human-in-the-loop

human-in-the-loop skill
vodailocz/kilo-kit-mcp · skills/productivity/human-in-the-loop/SKILL.md · Use when designing human approval gates for high-stakes agent actions. Keywords: human-in-the-loop, HITL, approval…
git:20260907.70ddb5c · audit A · 26 stars

Browse by kind, by grade A, or by owner.