constellation-works/orbit
Local-first delivery layer for AI coding agents. Your agent files the work as a task, and Orbit runs it in a sandboxed worktree with file locks and review gates. Every run ends in a pull request, with an audit log of every step. Works with
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code $ claude mcp add orbit -- orbit mcp serve --operator $ npx degit constellation-works/orbit/.claude ./rig-orbit # inspect, then merge into .claude/
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add orbit -- orbit mcp serve --operator $ npx degit constellation-works/orbit/crates/orbit-core/assets/skills/orbit-orchestrate .claude/skills/orbit-orchestrate $ npx degit constellation-works/orbit/crates/orbit-core/assets/skills/orbit-setup .claude/skills/orbit-setup $ npx degit constellation-works/orbit/crates/orbit-core/assets/skills/orbit .claude/skills/orbit
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"deny": [
"Read(./.orbit/tasks/**)",
"Read(./.orbit/runs/**)",
"Read(./.orbit/audit/**)",
"Read(./.orbit/diagnostics/**)",
"Read(./.orbit/**/orbit.db*)",
"Read(./target/**)",
"Read(./node_modules/**)",
"Read(./**/node_modules/**)",
"Read(./dist/**)",
"Read(./build/**)",
"Read(./website/dist/**)",
"Read(./.astro/**)",
"Read(./.ruff_cache/**)",
"Read(./benchmarks/**/runs/**)",
"Read(./benchmarks/**/tasks/**)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| orbit | binary | 2.5k |
Skills (3)
Permissions
deny (15)
Read(./.orbit/tasks/**)
Read(./.orbit/runs/**)
Read(./.orbit/audit/**)
Read(./.orbit/diagnostics/**)
Read(./.orbit/**/orbit.db*)
Read(./target/**)
Read(./node_modules/**)
Read(./**/node_modules/**)
Read(./dist/**)
Read(./build/**)
Read(./website/dist/**)
Read(./.astro/**)
Read(./.ruff_cache/**)
Read(./benchmarks/**/runs/**)
Read(./benchmarks/**/tasks/**)
ask (0)
—
allow (12)
mcp__orbit__orbit_search
mcp__orbit__orbit_friction_add
mcp__orbit__orbit_learning_add
mcp__orbit__orbit_learning_comment_add
mcp__orbit__orbit_learning_comment_list
mcp__orbit__orbit_learning_show
mcp__orbit__orbit_learning_update
mcp__orbit__orbit_learning_upvote
mcp__orbit__orbit_task_add
mcp__orbit__orbit_task_artifact_put
mcp__orbit__orbit_task_list
mcp__orbit__orbit_task_show
Similar rigs
simota/agent-skills
90 specialist AI agents + 3 project-local extensions for Claude Code / Codex CLI / Antigravity CLI (agy). Anthropic Agent Skills spec-aligned, hub-spoke orchestration via Nexus with 49 Recipes and 11 Skill Packs. Covers development, securit
Pragmatist 2.6k tok ·
anomalyco/opencode
The open source coding agent.
Pragmatist 4.2k tok ·
DietrichGebert/ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Pragmatist 1.6k tok ·
Shubhamsaboo/awesome-llm-apps
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
Pragmatist 4.2k tok ·