mirror of
https://github.com/openprose/prose.git
synced 2026-09-19 05:55:05 +08:00
dan
f961d852e9
Capture the agent-observatory Reactor learnings as authoring doctrine, scoped to multi-node Reactor pipelines so they are not over-applied. guidance/authoring.md gains a `## Cost and Context Discipline` section (tier with a cheap gatekeeper; bound each narrow render to its inline input; validate the cost-shape; keep renders cheap-model-small) plus four matching anti-patterns. SKILL.md's Authoring Guidance points to it for continuous / fan-out / high-event-volume pipelines. Opens with an explicit trigger and a Tenet-2 caveat: it applies to the narrow-transform renders that dominate a pipeline's volume, not to one-shot functions or single responsibilities, and a render whose job is to explore should still explore. CLI/version gotchas are deliberately left to reactor.md, not authoring doctrine. Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
purpose, related
| purpose | related | ||
|---|---|---|---|
| Bundled OpenProse skill definitions distributed with the prose repo — open-prose VM |
|
skills
Bundled OpenProse skill definitions shipped with the language specification repo. In environments with npx skills, each subdirectory can be installed as a skill; in Codex, the same files can be loaded through the repository-local AGENTS.md entry point.
Contents
open-prose/— the OpenProse VM skill; defines the*.prose.mdservice/system/test/pattern contract format, Forme wiring, ProseScript, state backends, primitives, package libraries, examples, and VM guidance. This skill is the canonical definition of what the OpenProse VM is; OpenProse Cloud is the hosted execution service that implements this spec.