Build embeddable Rust coding agents with Cersei
Compose coding-agent primitives in Rust, including tool execution, LLM streaming, sub-agent orchestration, memory, and MCP support, as an embeddable application workflow.
npx skills add agentskillexchange/skills --skill build-embeddable-rust-coding-agents-with-cersei
cargo add cersei, configure a supported model provider from environment credentials, import cersei::prelude::*, wire coding tools and a permission policy, then run repository tasks from the Rust application.Use Cersei when the job is to build or embed a coding agent inside a Rust application instead of driving a prebuilt coding CLI manually. The operator workflow is concrete: add the Cersei crate, choose a model provider, wire coding tools and permission policy, run repository tasks from application code, and inspect the generated output or changes. The scope boundary is a custom-agent build workflow for Rust teams that need reusable coding-agent primitives, not a general Rust library listing or a replacement for using Claude Code, Codex, or OpenCode directly.
What this skill actually does
Inputs and prerequisites: Rust toolchain, Cargo, model provider credentials, optional MCP-compatible tools.
Setup notes: Add the crate with cargo add cersei , configure a supported model provider from environment credentials, import cersei::prelude::* , wire coding tools and a permission policy, then run repository tasks from the Rust application.
Source and verification boundary: use https://cersei.pacifio.dev/docs as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a Custom Agents workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.