@morphllm/morph-setup 1.0.0 → 1.0.1

package/.agents/skills/code-edit/SKILL.md

@@ -0,0 +1,30 @@
+---
+name: code-edit
+description: Use Fast Apply (edit_file) for precise edits without reading full files.
+metadata:
+  author: morph
+  version: "0.1.0"
+  argument-hint: <file-or-change>
+---
+
+# Code Edit
+
+Prefer `edit_file` for modifications. Minimize full-file reads.
+
+## When To Use
+
+- The user requests code changes.
+- You can target specific files/functions.
+- You need to avoid context pollution.
+
+## Steps
+
+1. Locate the target file(s) (WarpGrep if needed).
+2. Read the smallest necessary snippet(s).
+3. Use `edit_file` with minimal context and `// ... existing code ...` placeholders.
+4. Re-run relevant checks (tests/build/lint) if available.
+
+## Notes
+
+- Keep edits small and surgical.
+- Prefer adding one change per call.

package/.agents/skills/explore/SKILL.md

@@ -0,0 +1,30 @@
+---
+name: explore
+description: Use this skill when the user asks you something that requires searching a code base
+metadata:
+  author: morph
+  version: "0.1.0"
+  argument-hint: <question>
+---
+
+# Explore
+
+Use WarpGrep to explore a codebase, this saves time and tokens.
+
+## When To Use
+
+- The user asks "how does this work?" or "where is X implemented?", anything that involves reading/tracing code
+- You need entry points, data flow, or ownership of a behavior.
+- Keyword grep is likely to miss the relevant files.
+
+## Steps
+
+1. Translate the user question into a tight semantic query.
+2. Run `warpgrep_codebase_search` against the repo root.
+3. Read the returned files/sections.
+4. Summarize the flow with concrete file paths.
+5. If changes are requested, propose the smallest edit plan and then execute.
+
+## Query Template
+
+"Find the entry points and data flow for <X>. Include router/handlers, config, and tests."

package/.agents/skills/feature-research/SKILL.md

@@ -0,0 +1,34 @@
+---
+name: feature-research
+description: Research existing architecture before implementing a complex feature.
+metadata:
+  author: morph
+  version: "0.1.0"
+  argument-hint: <feature>
+---
+
+# Feature Research
+
+Before implementing a complex feature, use WarpGrep to avoid duplicating patterns and to match existing conventions.
+
+## When To Use
+
+- New feature spans multiple modules/services.
+- You need to find existing patterns for similar features.
+- You need to identify API boundaries, data models, and tests.
+
+## Steps
+
+1. Identify the likely "shape" of the feature (routes, state, DB, background jobs, UI).
+2. Run `warpgrep_codebase_search` with a query that asks for similar features and related files.
+3. Extract:
+   - Existing patterns to reuse
+   - Integration points
+   - Config/feature-flag conventions
+   - Tests to mirror
+4. Propose an implementation plan that matches the repo.
+5. Implement.
+
+## Query Template
+
+"Find existing implementations similar to <feature>. Include endpoints, data models, background tasks, and tests."

package/dist/index.js

@@ -925,7 +925,7 @@ async function showMorphSplash() {
   process.stdout.write("\n");
 }
 function getBundledSkillsDir() {
-  return path3.resolve(__dirname, "..", "skills");
+  return path3.resolve(__dirname, "..", ".agents", "skills");
 }
 function getAllAgentTypes() {
   return Object.keys(agents);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@morphllm/morph-setup",
-  "version": "1.0.0",
+  "version": "1.0.1",
   "description": "Install Morph MCP and bundled skills onto coding agents",
   "type": "module",
   "bin": {
@@ -11,7 +11,7 @@
   },
   "files": [
     "dist",
-    "skills",
+    ".agents",
     "README.md"
   ],
   "scripts": {