starlight-intelligence
v0.3.0by frankxai · author: Starlight Intelligence Systems
A governed venture control plane for portfolio intelligence, execution, evidence, and decisions.
Package we checked
The manifest we fetched is plugins/starlight-intelligence/plugin.json in frankxai/Starlight-Intelligence-System. The plugin root is the directory that holds that file. Its $schema is https://agent-plugins.org/schemas/1.0.0/plugin.schema.json. The manifest lists 4 skills (starlight-command-center, starlight-decision-ledger, starlight-execution, starlight-knowledge) and no MCP servers. Extension keys: com.openai.
What starlight-intelligence does, in the publisher's words
Starlight provides four portable skills and a governed MCP implementation for portfolio intelligence, execution, evidence and decisions. Version 0.3 adds a portable root manifest, connected capability discovery and four brand-scoped workflow handoffs.
The private Worker implementation requires Cloudflare Access and tenant-scoped Supabase setup. Its public /healthz probe returned 404 on 4 October 2026; source verification does not establish a live private service. The separate public planning MCP and Academy MCP responded to initialize and four-tool discovery; a public Starlight catalog read also passed.
plugin.json follows Agent Plugins 1.0. Skills use the fixed skills/ directory, and the OpenAI interface lives under extensions.com.openai. The existing.codex-plugin/plugin.json remains synchronized for legacy hosts. Existing starter prompts are preserved. No unverified connection is activated by the portable manifest.
From the project README, punctuation lightly normalized · Open the README on GitHub
- Skills
- 4
- MCP servers
- 0
- Stars
- 0
- License
- MIT
Links
Skills · 4
- starlight-command-center
- Inspect a venture portfolio, identify operating pressure, and render a Starlight command center when the user asks for status, priorities, risks, or a visual operating view.
- starlight-decision-ledger
- Preserve a consequential venture decision, its tradeoffs, owner, review date, and supporting evidence when the user asks to decide, approve, reject, document, or audit a decision.
- starlight-execution
- Convert objectives into governed work items and move existing work through explicit states when the user asks to plan, assign, start, block, complete, or cancel execution.
- starlight-knowledge
- Retrieve records from the Starlight operating graph when the user asks what is known about a venture, objective, work item, decision, or piece of evidence.
Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.
Category
Other. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.
Keywords
venture-os · portfolio-intelligence · decision-ledger · agent-governance
Related by publisher and keywords
Build distinctive music, AI lab and AI tool pages from nine editable examples and focused v0 briefs.
Practice with Academy teaching guides, preserve evidence and connect canonical AI Architect delivery in your own workspace.
Design valuable Starlight agents with constitutional foundations, architecture decisions, activation prompts, scoped contracts and verifiable evidence. Includes Foundry design workflows and an in-process guardrail reference; production runtime integration is separate.
Build and restore portable agent skills and packages with source-backed ecosystem research, worked examples and inspectable package checks.
Practice human judgment, agentic systems and scientific inference with portable mission records; design departments and test workflow evidence.
Design portable skills and bounded agent systems, with an optional compile-and-proof handoff to a Starlight Foundry runtime.
[](https://agentpluginsdirectory.com/plugins/starlight-intelligence)✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.