rig-bundles-and-shareable-artifacts — Claude Code skill: install
This skill covers creating, inspecting, and installing OpenRig bundles that package a rig topology with its workflow. Use it when preparing a proven setup for reuse in another environment.
npx skills add mvschwarz/openrig --skill rig-bundles-and-shareable-artifacts -a claude-codeWhat rig-bundles-and-shareable-artifacts does
The skill explains what a bundle can contain: rig, agent, and workflow specs, startup files, skill references, operating modes, and proof expectations. It draws a practical line between bundles and extensions. A bundle describes the rig structure and workflow; an extension adds behavior to a user workspace or runtime.
It also covers portability checks, including hidden dependencies on local paths, providers, or credentials, excess machine-specific state, and missing proof expectations. The suggested proof installs the bundle into a clean OpenRig environment, instantiates it, checks the expected seats and workflow mode, then runs a small smoke test. A bundle is the wrong choice for runtime commands, views, or dashboards; those belong in an extension.
Use rig bundle inspect to review what installation will create before making changes. The skill also discusses rig bundle create and rig bundle install, and how proven lab patterns can become reusable workflows without turning each one into a daemon feature.
What it helps with
- package a proven OpenRig setup for reuse
- tell a bundle apart from an extension
- spot dependencies on local paths or credentials
- verify a bundle in a clean OpenRig environment
- define proof expectations for a bundled workflow
Example prompts for the agent
- Help me turn this proven OpenRig setup into a reusable bundle and decide what it should contain.
- Audit this bundle for dependencies on my machine's paths or credentials.
- Should I use a bundle or an extension to add a command to the runtime?
How to install rig-bundles-and-shareable-artifacts
1Skills CLI (Vercel)
npx skills add mvschwarz/openrig --skill rig-bundles-and-shareable-artifacts -a claude-code2Manually: put the files in place
~/.claude/skills/rig-bundles-and-shareable-artifacts/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/rig-bundles-and-shareable-artifacts/
1Skills CLI (Vercel)
npx skills add mvschwarz/openrig --skill rig-bundles-and-shareable-artifacts -a codex2Manually: put the files in place
.agents/skills/rig-bundles-and-shareable-artifacts/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add mvschwarz/openrig --skill rig-bundles-and-shareable-artifacts -a cursor2Manually: put the files in place
.cursor/skills/rig-bundles-and-shareable-artifacts/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install mvschwarz/openrig rig-bundles-and-shareable-artifacts2Manually: put the files in place
.github/skills/rig-bundles-and-shareable-artifacts/SKILL.md1Skills CLI (Vercel)
npx skills add mvschwarz/openrig --skill rig-bundles-and-shareable-artifacts -a gemini-cli2Platform CLI
gemini skills install https://github.com/mvschwarz/openrig --path skills/_canonical/core/rig-bundles-and-shareable-artifactsManually: put the files in place
.devin/skills/rig-bundles-and-shareable-artifacts/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add mvschwarz/openrig --skill rig-bundles-and-shareable-artifacts -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about rig-bundles-and-shareable-artifacts
How do I install rig-bundles-and-shareable-artifacts in Claude Code?
Run npx skills add mvschwarz/openrig --skill rig-bundles-and-shareable-artifacts -a claude-code. The skill file is at ~/.claude/skills/rig-bundles-and-shareable-artifacts/SKILL.md.
What does rig-bundles-and-shareable-artifacts do?
It explains how to create, inspect, and install OpenRig bundles, with guidance on portability checks. It also clarifies when a bundle fits and when an extension is needed to add runtime behavior.
How can I inspect a bundle before installing it?
Use rig bundle inspect <path> to see what the bundle would create without side effects.
Source text
SKILL.md · Apache-2.0
---
name: rig-bundles-and-shareable-artifacts
description: Use when authoring or installing a rig bundle (packaged, shareable artifact that instantiates an opinionated OpenRig topology + workflow), reasoning about the bundle vs extension boundary, or auditing a bundle for portability. Covers the 4 failure modes that prevent bundles from working anywhere but the operator's machine, and the inspect-before-install discipline.
metadata:
cli_surfaces_referenced:
- bundle create
- bundle inspect
- bundle install
openrig:
stage: factory-approved
sibling_skills:
- rig-lifecycle
- topology-mutation-and-seat-management
- seat-scaling-and-specialization
- cross-host-rig-commands
- sidecar-operator
- specification-system
- extension-and-user-workspace
---
# Rig Bundles and Shareable Artifacts
A **rig bundle** is a packaged, shareable artifact that can instantiate
an opinionated OpenRig topology and workflow. It may include:
- rig specs
- agent specs
- workflow specs
- startup files
- skills or skill references
- operating-mode declarations
- proof expectations
- supporting fragments
**Shareable artifact** is broader than bundle: specs, bundles, skills,
workflows, and extensions can all be shared. A bundle is the packaged
form for "load this topology and way of working."
## Use this when
- Authoring a bundle from a proven lab pattern
- Installing a bundle (`rig bundle install <path>`)
- Inspecting a bundle before install (`rig bundle inspect <path>`)
- Reasoning about bundle vs extension boundary (bundle declares topology + workflow; extension adds behavior)
- Auditing a bundle for portability — does it work on a clean OpenRig environment, or only the author's machine?
## Don't use this when
- The work is a one-off topology you won't reuse. Specs alone are sufficient.
- The intent is to add runtime behavior (commands, views, dashboards). Use `extension-and-user-workspace`, not bundles.
- You want to ship a workflow as a daemon feature. Bundle is the path *before* daemon promotion.
## The bundle vs extension boundary (load-bearing)
| Concept | Declares | Example |
|---|---|---|
| **Bundle** | Rig shape + workflow ("load this topology and way of working") | A Velocity Team bundle |
| **Extension** | Behavior added to user workspace/runtime | A custom command, view, or dashboard |
Don't confuse them. A bundle is *opinionated content*; an extension is
*added behavior*. Both can be shareable artifacts, but they're
structurally distinct.
## Failure modes (4)
1. **A bundle works only on the operator's machine** because paths, providers, or credentials are implicit. Bundles must be self-describing for a clean OpenRig environment.
2. **A bundle includes too much local state and becomes a backup archive instead of a reusable artifact.** Bundle is the *intended shape*, not the current state of one specific install.
3. **A bundle declares topology but omits proof expectations or workflow mode.** Topology alone doesn't tell users what "working as advertised" means.
4. **Users cannot inspect what a bundle will create before installing it.** `rig bundle inspect` must show what will be created without side effects.
## Proof standard
Proof should:
1. Install the bundle into a **clean OpenRig environment**
2. Instantiate it
3. Verify the expected seats and workflow mode
4. Run a small smoke proof that the topology behaves as advertised
## Bundle path → product
Bundles are how proven lab patterns become reusable product experiences:
```
local dogfood pattern
→ bundle (with manifest, parameterization, proof expectations)
→ installed by another user on clean OpenRig
→ opinionated workflow shipped without becoming a daemon feature
→ if dependable, graduate parts into core daemon
```
This is also how OpenRig can ship opinionated workflows **without making
every workflow a daemon feature.**
## See also
- `extension-and-user-workspace` skill — sibling primitive for user-owned behavior added to runtime; bundle vs extension boundary
- `specification-system` skill — rig specs / agent specs / workflow specs that bundles package
- `agent-starters` skill — bundles can include or reference Agent Starters
- `openrig-user` skill — `rig bundle create / inspect / install` CLI surface
© mvschwarz · Apache-2.0 · mvschwarz/openrig