claude-nexus 0.26.2 → 0.26.4

package/.claude-plugin/marketplace.json

@@ -7,7 +7,7 @@
     {
       "name": "claude-nexus",
       "description": "Agent orchestration plugin for Claude Code. Injects optimized context per agent role with minimal overhead.",
-      "version": "0.26.2",
+      "version": "0.26.4",
       "author": {
         "name": "kih"
       },

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-nexus",
-  "version": "0.26.2",
+  "version": "0.26.4",
   "description": "Agent orchestration plugin for Claude Code — optimized context injection per role",
   "author": {
     "name": "kih"

package/VERSION

@@ -1 +1 @@
-0.26.2
+0.26.4

package/hooks/hooks.json

@@ -79,6 +79,38 @@
         ]
       }
     ],
+    "PostToolUse": [
+      {
+        "matcher": "Edit",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/gate.cjs",
+            "timeout": 5
+          }
+        ]
+      },
+      {
+        "matcher": "Write",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/gate.cjs",
+            "timeout": 5
+          }
+        ]
+      },
+      {
+        "matcher": "NotebookEdit",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/gate.cjs",
+            "timeout": 5
+          }
+        ]
+      }
+    ],
     "Stop": [
       {
         "matcher": "*",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-nexus",
-  "version": "0.26.2",
+  "version": "0.26.4",
   "type": "module",
   "description": "Agent orchestration plugin for Claude Code — optimized context injection per role",
   "author": "kih",
@@ -39,7 +39,7 @@
     "@types/node": "^25.5.0",
     "esbuild": "^0.25.0",
     "typescript": "^5.8.0",
-    "@moreih29/nexus-core": "^0.7.0",
+    "@moreih29/nexus-core": "^0.9.0",
     "yaml": "^2"
   },
   "dependencies": {

package/skills/nx-init/SKILL.md

@@ -24,9 +24,9 @@ Scans the project and builds Nexus knowledge in the flat .nexus/ structure. On f
 
 ## Trigger
 
-- `/claude-nexus:nx-init` — full onboarding (or resume)
-- `/claude-nexus:nx-init --reset` — back up existing `.nexus/` knowledge and re-onboard
-- `/claude-nexus:nx-init --reset --cleanup` — show backup list + selective deletion
+- Manual trigger — full onboarding (or resume). See harness docs: slash_command_display.
+- Manual trigger with `--reset` flag — back up existing `.nexus/` knowledge and re-onboard. See harness docs: slash_command_display.
+- Manual trigger with `--reset --cleanup` flags — show backup list + selective deletion. See harness docs: slash_command_display.
 
 ---
 
@@ -59,9 +59,7 @@ Show backup directory list, let user select backups to delete.
 ```
 IF --reset --cleanup flag:
   Show list of .nexus/bak.*/ directories
-  Prompt user with options (using the harness's interactive prompt mechanism):
-    question: "Select a backup to delete (or cancel)"
-    options: [...backup list..., { label: "Cancel", description: "Exit without changes" }]
+  Prompt user with options via `AskUserQuestion({ question: "Select a backup to delete (or cancel)", options: [<backup list...>, {label: Cancel, description: "Exit without changes"}] })`.
   Delete selected backup and exit
 
 ELSE IF --reset flag:
@@ -170,15 +168,7 @@ On completion: "context knowledge N files generated"
 Check whether team custom rules are needed.
 
 ```
-prompt_user({
-  questions: [{
-    question: "Do you want to set up development rules now?",
-    options: [
-      { label: "Set up", description: "Coding conventions, test policy, commit rules, etc." },
-      { label: "Skip", description: "Can be added later via [rule] tag" }
-    ]
-  }]
-})
+AskUserQuestion({ question: "Do you want to set up development rules now?", options: [{label: "Set up", description: "Coding conventions, test policy, commit rules, etc."}, {label: Skip, description: "Can be added later via [rule] tag"}] })
 ```
 
 If "Set up": present a draft based on scan results → user confirms → save via the harness's file-creation primitive to `.nexus/rules/{topic}.md`.
@@ -200,7 +190,7 @@ Output a summary of the onboarding results.
 ### Next Steps
 - [plan] — research, analyze, and plan before execution
 - [run] — execute from a plan
-- /claude-nexus:nx-init --reset — re-run onboarding (existing knowledge will be backed up)
+- Manual re-run trigger with `--reset` flag — re-run onboarding (existing knowledge will be backed up). See harness docs: slash_command_display.
 ```
 
 
@@ -212,3 +202,17 @@ The "instruction file" in Claude Code is **CLAUDE.md** at the project root.
 - Project-specific content goes inside `<!-- PROJECT:START -->` / `<!-- PROJECT:END -->` markers.
 - The Nexus agent orchestration section is auto-managed inside `<!-- NEXUS:START -->` / `<!-- NEXUS:END -->` markers — do not edit manually.
 - If CLAUDE.md does not exist, create it with the PROJECT markers.
+
+
+---
+
+### Slash Command Display (Claude Code)
+
+Claude Code invokes skills via the `/claude-nexus:<skill-id>` slash form.
+
+- Typed by the user in the CLI: `/claude-nexus:nx-init`, `/claude-nexus:nx-setup`
+- Programmatic entry from another skill: `Skill({ skill: "claude-nexus:<skill-id>", args: "<optional>" })`
+- Tag-triggered entry (for skills with a `triggers` entry): the trigger tag (e.g. `[plan]`, `[run]`, `[sync]`) dispatches via gate.ts without requiring the slash form
+- `manual_only: true` skills (e.g. `nx-init`) expose only the slash form — no tag trigger
+
+When docs reference a skill to the user, prefer the slash form. When a skill dispatches another skill internally, prefer the `Skill` tool with the `claude-nexus:` prefix.

package/skills/nx-plan/SKILL.md

@@ -42,7 +42,7 @@ Facilitate structured multi-perspective analysis using subagents to decompose is
 
 ## Auto Mode (`[plan:auto]`)
 
-When triggered with `[plan:auto]` or invoked via `Skill({ args: "auto" })`, run the full planning process **without user interaction**:
+When triggered with `[plan:auto]` or invoked via `Skill({ skill: "claude-nexus:nx-plan", args: "auto" })`, run the full planning process **without user interaction**:
 
 1. **Research** — spawn researcher+Explore subagents (same as interactive)
 2. **Issue derivation** — Lead identifies issues from research
@@ -100,8 +100,8 @@ Understand code, core knowledge, and prior decisions before forming a planning a
 
 | Scenario | Approach |
 |----------|----------|
-| Codebase orientation | Spawn Explore agent (`subagent_type: "Explore"`) for file/code search |
-| External research needed | Spawn Researcher agent (`subagent_type: "claude-nexus:researcher"`) for web search |
+| Codebase orientation | `Agent({ subagent_type: "Explore", prompt: "<file/code search task>" })` for codebase exploration |
+| External research needed | `Agent({ subagent_type: "claude-nexus:researcher", prompt: "<research question>" })` for web search |
 | Both codebase and external | Spawn Explore + Researcher in parallel |
 
 - NEVER call `nx_plan_start` before research is complete.

package/skills/nx-run/SKILL.md

@@ -38,9 +38,9 @@ Execution norm that Lead follows when the user invokes the [run] tag. Composes s
 
 Register tasks for visual progress tracking (Ctrl+T):
 
-- **≤ 10 tasks**: `TaskCreate` per task
-- **> 10 tasks**: group by `plan_issue`, `TaskCreate` per group
-- Use `TaskUpdate` to reflect progress (`in_progress` / `completed`) as execution proceeds
+- **≤ 10 tasks**: `TaskCreate({ subject: "<per-task label>" })` per task
+- **> 10 tasks**: group by `plan_issue`, `TaskCreate({ subject: "<group label>" })` per group
+- Update the registered entry via `TaskUpdate({ taskId: <id>, status: "in_progress" })` / `TaskUpdate({ taskId: <id>, status: "completed" })` as execution proceeds
 - **Skip only if**: non-TTY environment (VSCode, headless)
 - **Known issue**: TUI may freeze during auto-compact (#27919) — task data on disk remains correct
 

package/skills/nx-sync/SKILL.md

@@ -51,8 +51,7 @@ Only update files where a concrete change is detected. If no staleness is found,
 Spawn Writer agent to update affected context documents:
 
 ```
-Agent({ subagent_type: "claude-nexus:writer", name: "writer-sync-context",
-  prompt: "Update .nexus/context/ documents based on the following changes. Read current files with the harness's file-reading primitive, then write updates with the harness's file-creation primitive. Changes: {change_manifest}" })
+Agent({ subagent_type: "claude-nexus:writer", name: "writer-sync-context", prompt: "Update .nexus/context/ documents based on the following changes. Read current files with the harness's file-reading primitive, then write updates with the harness's file-creation primitive. Changes: {change_manifest}" })
 ```
 
 The Writer agent: