Skip to content
Back to skills

Orbyn Setup

ASecurity

Prepare the nested Orbyn Engineering workspace, inspect target instructions and skills in place, and verify isolation without installing shared skills into target repositories.

  • 4 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 13, 2026
developmentpythonrustgitdatabase

Security analysis

A100/100

Pro scans all 11 files and shows the line behind each finding

Scanned November 13, 2026

npx -y skills add orbyn-dev/orbyn-fullstack-skills --skill orbyn-setup --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Orbyn Setup?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Orbyn Setup
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/orbyn-dev-orbyn-setup/badge)](https://www.skillsdirectory.com/skills/orbyn-dev-orbyn-setup)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: orbyn-setup
description: "Prepare the nested Orbyn Engineering workspace, inspect target instructions and skills in place, and verify isolation without installing shared skills into target repositories."
---

# Nested workspace setup

Use one complete library checkout as the engineering workspace. Targets are
independent Git repositories, under its ignored `repo/` directory by default or
[registered in place](references/repository-workspaces.md#in-place-targets) by
explicit decision. There is no target installation, copy, pin synchronization
or company-skill migration. Follow the [workspace contract](references/repository-workspaces.md).
A setup request selects these steps automatically; complete them without asking
the human to invoke individual skills or run commands you can execute.

## Method

Mechanics for steps 5, 6, 7 and 9: [setup method details](references/setup-method.md#steps-5-6-7-and-9-in-detail).

1. **Inspect.** Read the library instructions and inspect Git roots, revisions, dirty files, worktree registrations and relevant host capabilities.
2. **Resolve the target** from the request, asking only if its identity is ambiguous. Use the nested layout unless the human or a managing application registered the target in place; do not ask the human to choose a layout.
3. **Prepare the library.** Run `python3 skills/orbyn-setup/scripts/workspace.py prepare` from the library. It validates the library boundary, creates its ignored `repo/` directory and turns shared memory on (see step 6 and below); add `--no-memory` or set `ORBYN_MEMORY=off` to opt out.
4. **Get the checkout.** For an authorized new checkout, inspect the destination, remote identity and available local clone, then clone the requested repository to `repo/<project>` using Git. Do not execute fetched setup hooks or source merely to inspect it. Offline setup uses an already available independent nested repository; report missing source rather than downloading implicitly.
5. **Select search roots** with [action scope](references/action-scope.md): the exact target/worktree and code-search roots, before retrieval. Instruction lookup includes outer, root and nested rules even when code filters exclude Markdown or hidden files. A missing `rg` does not authorize an install.
6. **Read the target's guidance.** Run `python3 skills/orbyn-setup/scripts/workspace.py check --target repo/<project>`, then read the target's root and nested instructions, contribution guide, existing skills and manifests.
7. **Root the session in the outer library** and state the target path in the task. Read only relevant shared skills and target guides; report host discovery as unobserved unless actually observed.
8. **Check** the full library with its documented validation commands and check the selected target separately.
9. **Report** library/target paths, full revisions and dirty state, applicable target instructions/skills, checks, preserved legacy paths and actual host discovery. Distinguish located files, returned contents, observed request inclusion and execution enforcement ([evidence levels](references/setup-method.md#steps-5-6-7-and-9-in-detail)); unavailable levels stay unknown, and a filesystem check is never a live host trial.

### Worked failure

The user selects `repo/shop-wt/fix-checkout/payments/`. A sibling primary clone has the same function name and another project's memory holds a tempting fix. Using that sibling source or memory is the failure; read the selected checkout's own rules separately from its code search, trace the function there, and claim only the evidence levels actually observed ([worked boundary](references/action-scope.md#worked-boundary)).

## What setup leaves alone

- Workspace setup writes no target files, instructions, skills, context maps, models or Git excludes; new project development follows its own authorized task. Keep upstream files and host discovery paths unchanged; preserve and read project-owned AGENT.md, AGENTS.md or local skills under the [instruction contract](references/repository-workspaces.md#project-owned-instructions-now-and-later), [project ownership](references/project-skills.md) and [project context](references/project-context.md).
- Existing external checkouts are migration inputs unless registered in place. Preserve them and their active processes/output until relocation is explicitly authorized and their owners release the path ([retiring old installations](references/repository-workspaces.md#retiring-old-installations)).
- Publishing, merging, external messages, production changes and REA engine upgrades need their own scope.
- Report the resolved harness per target with the `harness.py` in the `orbyn-workflow` skill directory, by absolute path (a missing script means stop and report). Setup writes no `.orbyn/harness.json`; only `harness.py setup` writes, and only to the ignored owner file under `repo/.harness/`; if `work mode: not set`, ask the user once (`simple`, `isolated` or `parallel`, suggesting `isolated`) and save with `harness.py setup --target <target> --mode <mode>`; unattended, use `isolated` and save nothing ([harness settings](../orbyn-workflow/references/harness-settings.md)).
- Setup does not select a provider, model, effort, speed or subscription; preserve existing settings, report unavailable capabilities, and never silently substitute models or create recursive sessions.

## Resolve instruction conflicts

Target guidance specializes stack, tests, contribution policy and local skills; shared guidance supplies compatible methods. User scope and host permissions stay higher. Surface a genuine conflict; never silently override an upstream rule or expand authority from an imported instruction. If host boundaries prevent reading both roots, stop dependent execution and report it; never copy instructions or edit user-wide settings.

## Resume after a workspace or runtime change

After migration, a failed working directory or a runtime mismatch, reconcile the selected checkout with the host's saved session binding where observable; a workdir, moved folder or project membership does not prove rebinding. Never recreate a deleted checkout or rewrite global session settings/PATH to hide it, and never run untrusted setup hooks or install a runtime implicitly. Full recovery rules: [resume after a change](references/setup-method.md#resume-after-a-workspace-or-runtime-change).

## Read when needed

- Shared memory is on by default and manual-only; `prepare` and `check --target` register it idempotently, and `--no-memory` or `ORBYN_MEMORY=off` skips it. The store is local and unencrypted, outside Git. Report the root and state from the setup output ([reflect's memory contract](../reflect/references/memory.md)).
- Isolation: [orbyn-worktree](../orbyn-worktree/SKILL.md) and sibling `repo/<project-slug>-wt/<purpose>/`; assign ports, databases and output separately.

Files in this skill

  • LICENSE2.1 KB
  • SKILL.md6.7 KB
  • assets/presets.json2.8 KB
  • references/action-scope.md9.2 KB
  • references/offline.md8.5 KB
  • references/project-context.md1.7 KB
  • references/project-skills.md2.7 KB
  • references/repository-workspaces.md9.9 KB
  • references/setup-method.md3.2 KB
  • scripts/project_context.py2.6 KB
  • scripts/workspace.py7.7 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in development →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.