rote
01Plugin Claude Code
Compile AI agent skills into cheap, fast, deterministic pipelines that run without an LLM in the loop.
Plugin Claude Code
Compile AI agent skills into cheap, fast, deterministic pipelines that run without an LLM in the loop.
Instructions file CodexOpenCode
Instructions for trevhud/rote, covering agents.md — driving rote as an installed tool, invocation contract, preflight first: rote doctor, optional but recommended: rote baseline before compiling and rote compile is slow and costs money — plan for it.
Instructions file
Instructions for trevhud/rote, covering claude.md — context for ai collaborators, what rote is, three-layer architecture, layer 1 — the compiler agent (the "brain") and layer 2 — the driver layer (the "runtime for the agent").
Skill Claude CodeCodex
End-to-end BDR outreach campaign workflow. Use when running pharma/biotech outreach campaigns: finding leads via ZoomInfo, enriching conference attendee lists, uploading contacts to HubSpot CRM, managing lists, running exclusion checks (do-not-contact, recently emailed, active sequence), creating/editing sales email…
Plugin Claude Code
Compile fuzzy AI skills into deterministic workflows: /rote:compile compiles a SKILL.md into a runnable pipeline (Temporal, Cloudflare Workflows, or DBOS); /rote:serve exposes compiled pipelines as MCP tools.
Skill Claude CodeCodex
Compile an Anthropic-style skill — a directory with a SKILL.md and optional references/ — into a deterministic, runnable workflow via the rote CLI. Use when the user says "compile this skill", "graduate this skill" (the retired name for the same operation), "make this skill deterministic", "make this skill…
Skill Claude CodeCodex
Wire a compiled rote pipeline up as an MCP tool so Claude can trigger the deployed workflow directly. Use when the user says "register my compiled pipeline", "serve my pipelines over MCP", "trigger the workflow from Claude", "hook the pipeline up to Claude", or asks what to do after rote compile and deployment. Covers…
Skill Claude CodeCodex
Analyze an Anthropic-style skill bundle (SKILL.md + references) and produce a compilation plan that separates deterministic work into extracted Python modules, LLM-as-judge work into typed DSPy/BAML signatures, agentic work into bounded agent loops, and human-in-the-loop gates into durable suspend points. Emit the…