human-in-the-loop SKILL.md skillA

human-in-the-loop from mvschwarz/openrig is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add mvschwarz/openrig/human-in-the-loop@git:20260826.bdc404f

Pins git:20260826.bdc404f in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
mvschwarz/openrig
Path
packages/daemon/specs/agents/shared/skills/core/human-in-the-loop/SKILL.md
Versions recorded
2
Latest version
git:20260826.bdc404f, committed Aug 26, 2026
First version recorded
Aug 2, 2026
Size
5,255 bytes
Repository stars
8,889
License
Apache-2.0

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.

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

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

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_ghqhmbqdev5v2zne/14cf0c4a0dc89179121465d4b8d81d40406427351adcdc34f875097d1e6e9ab2.json

Then /plugin install human-in-the-loop@markdownregistry-ghqhmbqdev5v2zne in Claude Code. It installs git:20260826.bdc404f, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add mvschwarz/openrig/human-in-the-loop@sha256:14cf0c4a0dc89179

The line at the top of this page pins the label git:20260826.bdc404f, 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.

Badge

mdr badge

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

4 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in mvschwarz/openrig/human-in-the-loop since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of human-in-the-loop from somewhere else? Ask it: where did my human-in-the-loop come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 2 versions of this file, between Aug 2, 2026 and Aug 26, 2026, about one every 23 days.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20260826.bdc404f latest2026-08-26 bdc404f 5,255 BA view · diff
git:20260802.4c6d8882026-08-02 4c6d888 5,263 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the 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 · 8,889 stars · license Apache-2.0 · pushed 2026-11-18 · 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 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.

More from mvschwarz/openrig

developing-openrig SKILL.md skill
mvschwarz/openrig · .agents/skills/developing-openrig/SKILL.md · Use when changing OpenRig's own source in a clone of the openrig repository: finding which package or file owns a…
git:20261006.fcef78a · audit A · 8,889 stars
developing-openrig SKILL.md skill
mvschwarz/openrig · .claude/skills/developing-openrig/SKILL.md · Use when changing OpenRig's own source in a clone of the openrig repository: finding which package or file owns a…
git:20261006.fcef78a · audit A · 8,889 stars
DESIGN.md@docs DESIGN.md file
mvschwarz/openrig · docs/DESIGN.md
git:20261005.f6358a2 · audit A · 8,889 stars
agent-operated-software SKILL.md 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:20261109.46ba2f5 · audit A · 8,889 stars
agent-operated-workflows SKILL.md 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 · 8,889 stars
applying-a-permission-policy SKILL.md skill
mvschwarz/openrig · packages/daemon/assets/plugins/openrig-core/skills/applying-a-permission-policy/SKILL.md · Use before launching a team during agent-guided setup, or when a user asks to configure OpenRig command permissions…
git:20261006.141513e · audit A · 8,889 stars
claude-compaction-restore SKILL.md skill
mvschwarz/openrig · packages/daemon/assets/plugins/openrig-core/skills/claude-compaction-restore/SKILL.md · Use when a Claude Code session is about to compact, has just compacted, reached its context limit, resumed after…
git:20261113.0a6d575 · audit A · 8,889 stars
delegating-work SKILL.md 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:20261025.54bd485 · audit A · 8,889 stars
forming-an-openrig-mental-model SKILL.md 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:20261022.daa23d3 · audit A · 8,889 stars
loading-addressable-markdown SKILL.md 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 · 8,889 stars
messaging-the-human SKILL.md 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:20261115.c60575e · audit A · 8,889 stars
mission-slice-sop SKILL.md 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:20261117.29d4a62 · audit A · 8,889 stars

Every file in mvschwarz/openrig

Other files named human-in-the-loop

human-in-the-loop SKILL.md skill
mvschwarz/openrig · skills/_canonical/core/human-in-the-loop/SKILL.md · Use when classifying a slice closeout (auto-continue / human gate / park), routing a real decision to a human, or…
git:20260826.bdc404f · audit A · 8,889 stars
human-in-the-loop SKILL.md 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 · 28 stars

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