Show HN: theta-spec - a humble harness agnostic configuration spec A new open-source specification called theta-spec provides a declarative, harness-agnostic configuration standard for AI coding agents, allowing users to define the full configuration surface—including instructions, rules, tools, skills, and subagents—in a single `theta.toml` file. The project includes a reference implementation in Rust that resolves, locks, and casts the configuration to any supported agent harness, addressing the lack of a standard way to share, version, or reproduce agent configurations across different harnesses. The specification aims to enable reproducible configurations, simplify maintenance across harness updates, and provide a foundation for tooling to optimize how developers work with AI agents. theta-spec is a declarative, harness-agnostic configuration standard for AI coding agents. One theta.toml file defines the full configuration surface, i.e. instructions, rules, tools, skills, subagents. A protocol is specified for the lifecycle of this configuration file, and any theta-spec compliant implementation can resolve, lock, and cast it to any supported harness. is the default implementation of this spec — a Rust CLI that resolves, locks, and casts theta theta.toml to any supported harness. All the documentation for the specification is present here https://theta-spec.tamarillo.ai/ and can also be built and served locally by running uv run mkdocs serve --livereload Agent harnesses are here to stay. Each one ships its own configuration format but still all of them share similarities. Maintaining and declaring configurations is a burden. There is no standard way to share, version, or reproduce an agent configuration. Parametrizing the configuration surface into a single manifest: - Displays the exhaustive configuration at a glance - Provides an entrypoint for searching the resources that define an agent - Enables reproducible configurations between people and between agents - Makes mutation strategies explicit and diffable - Facilitates maintenance across harness updates - Enables a project lifecycle tool, which is why the theta CLI https://theta.tamarillo.ai/ exists A parametrized function and a well-defined cost function enables function approximation. If the goal is to optimize the way we work with agents, this is the first tiny step towards building the tooling needed to cover at least one gap, the parameters. Most of the spec is read-self-explanatory for anyone familiar with agent harnesses. A detailed and exhaustive description of each one of the defining fields can be found condensed here /tamarillo-ai/theta-spec/blob/main/docs/spec/manifest.md and also in the manifest section of this doc /tamarillo-ai/theta-spec/blob/main/docs/manifest/index.md . This is how a theta.toml looks: theta schema = "2026-04" agent name = "harness-researcher" description = "researches agent harness configurations across public repos" version = "0.1.0" authors = "ivan