agent-watchdog
Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a Codex session ID, Claude Code…
Run only when the user explicitly invokes /efficient-orchestrator (or the /efficient-frontier and /efficient-fable aliases). Keeps an expensive model (Fable, Opus, Astra, Sol) on planning, judgment and review while cheaper subagents do bounded research, coding, QA and log work.
Claude Code
$ npx -y skills add BuilderIO/skills --skill efficient-orchestrator --agent claude-code
Codex
$ npx skills add BuilderIO/skills --skill efficient-orchestrator -a codex -y
Cursor
$ npx skills add BuilderIO/skills --skill efficient-orchestrator -a cursor -y
Gemini CLI
$ npx skills add BuilderIO/skills --skill efficient-orchestrator -a gemini-cli -y
GitHub Copilot
$ npx skills add BuilderIO/skills --skill efficient-orchestrator -a github-copilot -y
OpenCode
$ npx skills add BuilderIO/skills --skill efficient-orchestrator -a opencode -y
Windsurf
$ npx skills add BuilderIO/skills --skill efficient-orchestrator -a windsurf -y
name: efficient-orchestrator description: Run only when the user explicitly invokes /efficient-orchestrator (or the /efficient-frontier and /efficient-fable aliases). Keeps an expensive model (Fable, Opus, Astra, Sol) on planning, judgment and review while cheaper subagents do bounded research, coding, QA and log work. Never self-activate. disable-model-invocation: true
Use this only when the user asks for it by name. Without that request, do the work yourself and don't spawn helpers.
The expensive main model plans, decides, integrates and reviews. Cheaper subagents do the token-heavy, bounded work.
| Main model | Cheap helpers | Use | | --- | --- | --- | | Claude Fable / Opus | `haiku` | search, scans, docs extraction, log reduction, mechanical edits, test and browser runs | | | `sonnet` | coding or analysis that needs judgment | | OpenAI Astra / Sol | `gpt-6.1-terra` low or medium | coding, QA, research, most delegated work | | | `gpt-6-luna` | bulk mechanical scans, only when Terra isn't needed |
Set the model and effort explicitly on every spawn; never let a helper inherit the expensive model. If the main model is already a cheap tier, don't use this skill.
1. Keep at the top: architecture, prioritization, ambiguity, risk, synthesis and final review. 2. Delegate: repo scans, research, narrow patches with clear file ownership, test and browser passes, failure clustering, log reduction. 3. Write each handoff as a self-contained packet: repo path, objective, scope and out-of-scope, files or search targets, verification command, return format, stop conditions. 4. Require compact returns: findings, changed files, commands run, evidence, open decisions. 5. Inspect the evidence that matters before claiming done. Delegated output is evidence, not a verdict.
helpers the same files.
Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a Codex session ID, Claude Code…
Open and operate Agent-Native workspace apps through Dispatch MCP, with inline app surfaces, browser-session authentication, and…
Alias for /efficient-orchestrator. Run only when the user explicitly invokes /efficient-fable; never self-activate.
Alias for /efficient-orchestrator. Run only when the user explicitly invokes /efficient-frontier; never self-activate.
Experimental workflow for babysitting one explicitly authorized pull or merge request. Use to monitor its live review state and…
Experimental workflow for collecting and triaging product feedback, product telemetry, runtime errors, and issue reports. Use…
Set up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI…