@webpresso/claude-plugin 3.1.16 → 3.1.17

package/.claude-plugin/marketplace.json

@@ -6,7 +6,7 @@
   },
   "metadata": {
     "description": "Webpresso agent-kit Claude Code plugin: blueprints, skills, hooks, MCP server",
-    "version": "3.1.16"
+    "version": "3.1.17"
   },
   "plugins": [
     {
@@ -34,5 +34,5 @@
       }
     }
   ],
-  "version": "3.1.16"
+  "version": "3.1.17"
 }

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "agent-kit",
-  "version": "3.1.16",
+  "version": "3.1.17",
   "description": "Webpresso agent-kit: blueprints, skills, lore commit protocol, tech-debt lifecycle",
   "author": {
     "name": "Webpresso",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@webpresso/claude-plugin",
-  "version": "3.1.16",
+  "version": "3.1.17",
   "private": false,
   "description": "Claude Code plugin adapter for Webpresso agent-kit skills, commands, and MCP runtime.",
   "homepage": "https://github.com/webpresso/agent-kit#readme",

package/plugin-skill-ownership.json

@@ -2,11 +2,11 @@
   "schemaVersion": 1,
   "host": "claude",
   "packageName": "@webpresso/claude-plugin",
-  "packageVersion": "3.1.16",
+  "packageVersion": "3.1.17",
   "runtimeDirs": [".claude/skills"],
   "skills": {
     "autopilot": {
-      "digest": "sha256:7fc1fe9f5fb5b8a3e755f8e3ac4b807e4f140288544ffcf39e4cbfdea984014d"
+      "digest": "sha256:9e0b47c8438fe7c8123bec3361fcb17fd2fcd818a840f46ea272a7712e4c0b10"
     },
     "autoresearch": {
       "digest": "sha256:b4d51cd53beb4a3271827172dfbd0b1d27bd58761ca07a35d49a5d6324b87fdf"
@@ -35,9 +35,6 @@
     "fix": {
       "digest": "sha256:e43dfad198f7279ebc2dca9e62f43fd960c783ca0ab25f133668fca13aed96b2"
     },
-    "goal": {
-      "digest": "sha256:85380b633cfaaff8ec1639dd3a88412a41920aae3e8531de95e2b79411926a18"
-    },
     "hooks-doctor": {
       "digest": "sha256:3bfb0af64ff6796c56d51e4cd2bede7fb24c869f89b292546ea13ad2f5d3bb73"
     },
@@ -77,6 +74,9 @@
     "tph": {
       "digest": "sha256:bed3684a850651534f315d355cdeae50d951c429817df0f105cccdb7f4e1561b"
     },
+    "ultragoal": {
+      "digest": "sha256:dc6d3b2bd48a494d7a5cd30ad9c6c9999989b9920ca06ccd1f86a7cfaff60d54"
+    },
     "verify": {
       "digest": "sha256:ce0dd3a77508d1bf11c805dec2de04e75b689201d376b2ff0fa957604d584500"
     }

package/skills/autopilot/SKILL.md

@@ -15,7 +15,7 @@ argument-hint: "<brief|force: brief>"
 
 # Autopilot
 
-Drive an approved brief through `plan -> execute -> qa -> validate -> land -> complete` using `wp goal run` and the current handoff.
+Drive an approved brief through `plan -> execute -> qa -> validate -> land -> complete` using `wp ultragoal run` and the current handoff.
 
 ## Vague gate
 
@@ -34,6 +34,6 @@ A brief is anchored when it includes a file path, symbol, issue number, test nam
    ```
 
 5. Land: require green PR checks, complete the blueprint in the same PR, merge, and run owner cleanup.
-6. Complete: stop only when `wp goal run` records terminal evidence.
+6. Complete: stop only when `wp ultragoal run` records terminal evidence.
 
-Resume from durable state after interruption. Obey `WP_GOAL_DISABLE=1`, iteration/error/validation caps, and repository ownership. The pipeline must never self-approve, directly mark tasks done, bypass evidence, or push to main. Keep every loop bounded and never increase timeouts.
+Resume from durable state after interruption. Obey `WP_ULTRAGOAL_DISABLE=1`, iteration/error/validation caps, and repository ownership. The pipeline must never self-approve, directly mark tasks done, bypass evidence, or push to main. Keep every loop bounded and never increase timeouts.

package/skills/ultragoal/SKILL.md

@@ -0,0 +1,27 @@
+---
+type: skill
+slug: ultragoal
+title: Ultragoal
+status: active
+scope: repo
+applies_to: [agents]
+related: [autopilot, plan-refine, verify]
+created: "2026-07-10"
+last_reviewed: "2026-07-10"
+name: ultragoal
+description: "Run durable multi-blueprint ultragoals through evidence-gated handoffs."
+argument-hint: "<new|status|handoff|run|cancel> [brief]"
+---
+
+# Ultragoal
+
+Use `wp ultragoal` as the durable controller for work spanning one or more blueprints.
+
+## Protocol
+
+1. Create or resume the ultragoal in a managed blueprint owner worktree.
+2. Read `wp ultragoal status`, execute only the current phase handoff, then call `wp ultragoal run` again.
+3. Complete blueprint tasks only through `wp_blueprint_task_verify` with passing evidence.
+4. Stop when the controller reports `complete`, `cancelled`, blocked guard exhaustion, or `WP_ULTRAGOAL_DISABLE=1`.
+
+The blueprint engine owns task status and approval gates. The ultragoal controller must never self-approve, directly mark a task done, bypass review provenance, or mutate the primary checkout. Keep every loop bounded and never increase timeouts.

package/skills/goal/SKILL.md

@@ -1,27 +0,0 @@
----
-type: skill
-slug: goal
-title: Goal
-status: active
-scope: repo
-applies_to: [agents]
-related: [autopilot, plan-refine, verify]
-created: "2026-07-10"
-last_reviewed: "2026-07-10"
-name: goal
-description: "Run durable multi-blueprint goals through evidence-gated handoffs."
-argument-hint: "<new|status|handoff|run|cancel> [brief]"
----
-
-# Goal
-
-Use `wp goal` as the durable controller for work spanning one or more blueprints.
-
-## Protocol
-
-1. Create or resume the goal in a managed blueprint owner worktree.
-2. Read `wp goal status`, execute only the current phase handoff, then call `wp goal run` again.
-3. Complete blueprint tasks only through `wp_blueprint_task_verify` with passing evidence.
-4. Stop when the controller reports `complete`, `cancelled`, blocked guard exhaustion, or `WP_GOAL_DISABLE=1`.
-
-The blueprint engine owns task status and approval gates. The goal controller must never self-approve, directly mark a task done, bypass review provenance, or mutate the primary checkout. Keep every loop bounded and never increase timeouts.