Release skill 0.18.1 with contract execution terminology

.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "open-prose",
   "description": "State what an agent must accomplish and which requirements it must satisfy. Reuse and combine Markdown contracts.",
-  "version": "0.18.0",
+  "version": "0.18.1",
   "license": "MIT",
   "homepage": "https://github.com/openprose/prose",
   "author": {

.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "open-prose",
-  "version": "0.18.0",
+  "version": "0.18.1",
   "description": "State what an agent must accomplish and which requirements it must satisfy. Reuse and combine Markdown contracts.",
   "license": "MIT",
   "homepage": "https://github.com/openprose/prose",

CHANGELOG.md

@@ -7,6 +7,16 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.18.1] - 2026-10-01 — open-prose skill & plugin
+
+### Changed
+
+- Explain contract authoring as expressing intent by composing requirements.
+- Use executor for the role performing work and evaluator for the role assessing whether requirements are satisfied. Evidence belongs in the result; assessment names the evaluation and its findings.
+- Distinguish successful execution from contract fulfillment and contract adequacy in authoring and interpreter guidance.
+
+The skill runtime contract remains 2. Existing source, return declarations and runtime interfaces need no migration.
+
 ## [0.17.0] - 2026-08-27 — open-prose skill & plugin
 
 ### Added

skills/open-prose/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: open-prose
-version: 0.18.0
+version: 0.18.1
 runtime_contract: 2
 description: |
   Activate when the user types `prose ...`, opens a `.prose.md` file with

skills/open-prose/changelog.md

@@ -47,6 +47,8 @@ plan.
 
 ## History
 
+- `v0.18.1`: **Contract execution and assessment terminology.** Contract authoring expresses intent by composing requirements. The executor performs work; the evaluator assesses whether requirements are satisfied. A result includes its supporting evidence, and an assessment records the evaluation and findings. Successful execution does not by itself establish contract fulfillment or adequacy. No source rewrite is required: preserve authored syntax, function return declarations, responsibility interfaces, saved records and `runtime_contract: 2`. Review explanatory prose when upgrading; do not rename protocol fields or historical evidence.
+
 - `v0.18.0`: **Example corpus made compiler-clean.** `id:` frontmatter is now
   optional on responsibilities and gateways: the slug is the identity by
   default, and a declared id is the source identity that survives filename and

tests/open-prose/skill-meta/skill-meta.test.ts

@@ -92,13 +92,13 @@ describe("skill-meta Markdown helpers", () => {
 describe("SKILL.md frontmatter — versioning", () => {
 	const fm = frontmatter(read("SKILL.md"));
 
-	it("pins version to 0.18.0", () => {
+	it("pins version to 0.18.1", () => {
 		// 0.15.0 was the Intelligent React overhaul;
 		// 0.16.0 removes the harness product surface from the skill.
 		// 0.17.0 introduces guided init/compose and the Compose std package.
 		// 0.18.0 makes id: optional, documents facet families, and brings the
 		// example corpus into conformance with the compiler.
-		expect(fm).toMatch(/^version:\s*0\.18\.0\s*$/m);
+		expect(fm).toMatch(/^version:\s*0\.18\.1\s*$/m);
 	});
 
 	it("bumps runtime_contract to 2", () => {