agentsclimarketplace

Opt shell install

Skill reopt-ai/reopt-skills/skills/opt-shell-install

Install or upgrade @reopt-ai/opt-shell — the runtime product-frame layer (workspace recipes, density/contentWidth/navigation/motion policy, data-engine adapters, shared state boundaries). Formerly @reopt-ai/opt-harness. Auto-branches by current install state. Triggers on "opt-shell install", "opt-shell init", "opt-shell setup", "shell install", "app shell setup", "workspace recipe", "opt-shell upgrade", "opt-shell update", plus legacy "opt-harness install", "harness install", "harness setup".From its SKILL.md

Install
npx -y skills add reopt-ai/reopt-skills --skill opt-shell-install

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

  • reads credentialsReads from 1 credential source: `.npmrc`.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
  • runs commandsInstructs the agent to run 2 commands, including `npm config get @reopt-ai:registry` and 1 more.

SKILL.md

5.4 KB, ~1.3k tokens by cl100k_base, as published. Nobody here has run it

opt-shell Install

This is NOT the opt-shell you know. @reopt-ai/opt-shell (formerly @reopt-ai/opt-harness) is the runtime product-frame layer between opt-ui and product screens. It ships no dist/docs/ — read node_modules/@reopt-ai/opt-shell/shell-llms.txt (agent guide) and README.md before writing code.

When to apply

Consumer project depends on @reopt-ai/opt-shell. Triggers: "install", "init", "setup", "upgrade", "update" — with shell / opt-shell (or the legacy harness / opt-harness). @reopt-ai/opt-harness was renamed to @reopt-ai/opt-shell; if a project still references opt-harness, migrate the dependency first.

What opt-shell provides

AreaPattern
Workspace recipesDashboardWorkspace, ListWorkspace, DetailWorkspace, EditorWorkspace, landing — pick via the decision tree in shell-llms.txt
Non-recipe surfaceShellFullscreenToolSurface (full-viewport tools — code editor, canvas)
Policydensity, contentWidth (full / wide / normal / narrow), navigationMode, motion
Adaptersdata-engine wrappers supplying loading / empty / error chrome
State UXshared state boundaries; every recipe requires header + content slots
Authoring audit@reopt-ai/opt-cli/audit + opt harness commands; published opt-shell 1.0.0 has no ./audit export

Invocation

/opt-shell-install              # Auto-branch (missing → init, installed → upgrade)
/opt-shell-install --upgrade    # Explicit upgrade
/opt-shell-install --check      # Analyze only

Step 1 — Pin agent rules into AGENTS.md / CLAUDE.md

Source: the module's own agent-rules file once it ships one (@reopt-ai/opt-shell ships shell-llms.txt, an agent guide, but not a marker-block file as of 1.0.0). Fallback: agent-rules.md bundled with this skill. Wrap content between:

<!-- BEGIN:reopt/opt-shell-agent-rules -->
…content from source…
<!-- END:reopt/opt-shell-agent-rules -->

Idempotent: replace only between markers.

Step 2 — Consumer-side setup (this skill owns; docs cannot)

  1. Public npm registry — no token or scoped .npmrc entry is required. Inspect the project .npmrc and npm config get @reopt-ai:registry; if the scope still resolves to GitHub Packages, remove only the legacy project entry @reopt-ai:registry=https://npm.pkg.github.com. Preserve unrelated registry/auth settings, and ask before changing user/global npm config.

  2. Peers — opt-shell's peerDependencies (install / run their skills first if missing):

    • Required: @reopt-ai/opt-palette (theme engine), react / react-dom 19+
    • Optional (only if you use that adapter): @reopt-ai/opt-datagrid (/opt-datagrid-install), @reopt-ai/opt-editor (/opt-editor-install), @reopt-ai/opt-calendar

    opt-ui tokens come in transitively through opt-palette — run /opt-ui-install if the theme layer is missing.

  3. App wiring — properties of the consumer app:

    • A workspace recipe at the screen root (header + content slots are mandatory).
    • A shell manifest / policy config (density, contentWidth, navigationMode, motion).
    • Adapters wired to your data engines wherever loading / empty / error chrome is needed.

Step 3 — Route to module docs

opt-shell ships no dist/docs/. Route to shell-llms.txt (agent guide) and README.md.

Task signalRead
Recipe decision tree, slot rules, policyshell-llms.txt
Component / prop API, exports (., ./core, ./meta)README.md
Authoring audit / scoring@reopt-ai/opt-cli/audit; `npx @reopt-ai/opt-cli harness check
Breaking changes per versionCHANGELOG.md

Pipeline (auto-branch)

#StepInitUpgrade
1Detect current state (incl. legacy opt-harness dep)
2Public-registry preflight + legacy override cleanup
3Install / update package
4Peer check (opt-palette required; opt-datagrid / opt-editor / opt-calendar optional)
5Shell manifest / policy config
6First workspace recipe
7Breaking-change edits
8Verify + summary

Safety

  • Never upgrade without an impact scan.
  • Confirm before overwriting existing files.
  • Apply breaking-change edits in logical groups, never bulk.
  • Do not finish until tsc --noEmit passes.
  • Never commit — do not commit or push without an explicit request.

Verify

  1. npx tsc --noEmit passes.
  2. App boots into the chosen workspace recipe (header + content slots filled); policy (density / contentWidth / navigationMode) applies.
  3. (If an adapter is used) the data-grid or editor adapter renders the peer's content with shell chrome (loading / empty / error states).

What ships with it: 3 files

3.0 KB alongside SKILL.md

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.