docs: use npx ai-devkit@latest across guides and templates

codeaholicguy · codeaholicguy · commit 03385eddcb69 · 2026-02-21T17:17:34.000+01:00
diff --git a/AGENTS.md b/AGENTS.md
@@ -57,7 +57,7 @@ The AI assistant should proactively use knowledge memory throughout all interact
 
 **How to search**:
 - Use `memory.searchKnowledge` MCP tool with relevant keywords, tags, and scope
-- If MCP tools are unavailable, use `npx ai-devkit memory search` CLI command (see memory skill for details)
+- If MCP tools are unavailable, use `npx ai-devkit@latest memory search` CLI command (see memory skill for details)
 - Example: Search for "authentication patterns" when implementing auth features
 
 ### When to Store Memory
@@ -68,7 +68,7 @@ The AI assistant should proactively use knowledge memory throughout all interact
 
 **How to store**:
 - Use `memory.storeKnowledge` MCP tool
-- If MCP tools are unavailable, use `npx ai-devkit memory store` CLI command (see memory skill for details)
+- If MCP tools are unavailable, use `npx ai-devkit@latest memory store` CLI command (see memory skill for details)
 - Include clear title, detailed content, relevant tags, and appropriate scope
 - Make knowledge specific and actionable, not generic advice
 
diff --git a/CLAUDE.md b/CLAUDE.md
@@ -57,7 +57,7 @@ The AI assistant should proactively use knowledge memory throughout all interact
 
 **How to search**:
 - Use `memory.searchKnowledge` MCP tool with relevant keywords, tags, and scope
-- If MCP tools are unavailable, use `npx ai-devkit memory search` CLI command (see memory skill for details)
+- If MCP tools are unavailable, use `npx ai-devkit@latest memory search` CLI command (see memory skill for details)
 - Example: Search for "authentication patterns" when implementing auth features
 
 ### When to Store Memory
@@ -68,7 +68,7 @@ The AI assistant should proactively use knowledge memory throughout all interact
 
 **How to store**:
 - Use `memory.storeKnowledge` MCP tool
-- If MCP tools are unavailable, use `npx ai-devkit memory store` CLI command (see memory skill for details)
+- If MCP tools are unavailable, use `npx ai-devkit@latest memory store` CLI command (see memory skill for details)
 - Include clear title, detailed content, relevant tags, and appropriate scope
 - Make knowledge specific and actionable, not generic advice
 
diff --git a/README.md b/README.md
@@ -11,7 +11,7 @@ AI DevKit helps AI coding agents work more effectively with your codebase. It pr
 ## Quick Start
 
 ```bash
-npx ai-devkit init
+npx ai-devkit@latest init
 ```
 
 This launches an interactive setup wizard that configures your project for AI-assisted development in under a minute.
diff --git a/commands/remember.md b/commands/remember.md
@@ -6,5 +6,5 @@ When I say "remember this" or want to save a reusable rule, help me store it in
 
 1. **Capture Knowledge** — If not already provided, ask for: a short explicit title (5-12 words), detailed content (markdown, examples encouraged), optional tags (keywords like "api", "testing"), and optional scope (`global`, `project:<name>`, `repo:<name>`). If vague, ask follow-ups to make it specific and actionable.
 2. **Validate Quality** — Ensure it is specific and reusable (not generic advice). Avoid storing secrets or sensitive data.
-3. **Store** — Call `memory.storeKnowledge` with title, content, tags, scope. If MCP tools are unavailable, use `npx ai-devkit memory store` instead.
+3. **Store** — Call `memory.storeKnowledge` with title, content, tags, scope. If MCP tools are unavailable, use `npx ai-devkit@latest memory store` instead.
 4. **Confirm** — Summarize what was saved and offer to store more knowledge if needed.
diff --git a/packages/cli/README.md b/packages/cli/README.md
@@ -16,7 +16,7 @@ The command-line interface for **AI DevKit** — set up and manage AI-assisted d
 
 ```bash
 # Run directly (no install needed)
-npx ai-devkit init
+npx ai-devkit@latest init
 
 # Or install globally
 npm install -g ai-devkit
diff --git a/packages/cli/src/__tests__/services/lint/rules/base-docs.rule.lint.test.ts b/packages/cli/src/__tests__/services/lint/rules/base-docs.rule.lint.test.ts
@@ -27,6 +27,6 @@ describe('base docs rule', () => {
 
     expect(checks).toHaveLength(5);
     expect(checks.every(check => check.level === 'miss')).toBe(true);
-    expect(checks[0].fix).toBe('Run: npx ai-devkit init');
+    expect(checks[0].fix).toBe('Run: npx ai-devkit@latest init');
   });
 });
diff --git a/packages/cli/src/services/lint/rules/base-docs.rule.ts b/packages/cli/src/services/lint/rules/base-docs.rule.ts
@@ -9,7 +9,7 @@ export function runBaseDocsRules(cwd: string, deps: LintDependencies): LintCheck
     idPrefix: 'base',
     category: 'base-docs',
     filePathForPhase: (phase: string) => `${DOCS_DIR}/${phase}/README.md`,
-    missingFix: 'Run: npx ai-devkit init',
+    missingFix: 'Run: npx ai-devkit@latest init',
     deps
   });
 }
diff --git a/packages/cli/templates/commands/remember.md b/packages/cli/templates/commands/remember.md
@@ -6,5 +6,5 @@ When I say "remember this" or want to save a reusable rule, help me store it in
 
 1. **Capture Knowledge** — If not already provided, ask for: a short explicit title (5-12 words), detailed content (markdown, examples encouraged), optional tags (keywords like "api", "testing"), and optional scope (`global`, `project:<name>`, `repo:<name>`). If vague, ask follow-ups to make it specific and actionable.
 2. **Validate Quality** — Ensure it is specific and reusable (not generic advice). Avoid storing secrets or sensitive data.
-3. **Store** — Call `memory.storeKnowledge` with title, content, tags, scope. If MCP tools are unavailable, use `npx ai-devkit memory store` instead.
+3. **Store** — Call `memory.storeKnowledge` with title, content, tags, scope. If MCP tools are unavailable, use `npx ai-devkit@latest memory store` instead.
 4. **Confirm** — Summarize what was saved and offer to store more knowledge if needed.
diff --git a/packages/cli/templates/env/base.md b/packages/cli/templates/env/base.md
@@ -57,7 +57,7 @@ The AI assistant should proactively use knowledge memory throughout all interact
 
 **How to search**:
 - Use `memory.searchKnowledge` MCP tool with relevant keywords, tags, and scope
-- If MCP tools are unavailable, use `npx ai-devkit memory search` CLI command (see memory skill for details)
+- If MCP tools are unavailable, use `npx ai-devkit@latest memory search` CLI command (see memory skill for details)
 - Example: Search for "authentication patterns" when implementing auth features
 
 ### When to Store Memory
@@ -68,7 +68,7 @@ The AI assistant should proactively use knowledge memory throughout all interact
 
 **How to store**:
 - Use `memory.storeKnowledge` MCP tool
-- If MCP tools are unavailable, use `npx ai-devkit memory store` CLI command (see memory skill for details)
+- If MCP tools are unavailable, use `npx ai-devkit@latest memory store` CLI command (see memory skill for details)
 - Include clear title, detailed content, relevant tags, and appropriate scope
 - Make knowledge specific and actionable, not generic advice
 
diff --git a/skills/dev-lifecycle/SKILL.md b/skills/dev-lifecycle/SKILL.md
@@ -9,7 +9,7 @@ Sequential phases producing docs in `docs/ai/`. Flow: 1→2→3→4→(5 after e
 
 ## Prerequisite
 
-Before starting any phase, run `scripts/check-docs.sh` to verify the base `docs/ai/` structure exists. If it fails, run `npx ai-devkit init` first. Do not proceed until all checks pass.
+Before starting any phase, run `scripts/check-docs.sh` to verify the base `docs/ai/` structure exists. If it fails, run `npx ai-devkit@latest init` first. Do not proceed until all checks pass.
 
 For a **new feature start** (Phase 1 or `/new-requirement`), apply the shared worktree setup in [references/worktree-setup.md](references/worktree-setup.md) before phase work. This setup is worktree-first by default and includes explicit no-worktree fallback, context verification, and dependency bootstrap.
 
@@ -50,10 +50,10 @@ Phases: `requirements/`, `design/`, `planning/`, `implementation/`, `testing/`.
 
 ## Memory Integration
 
-Use `npx ai-devkit memory` CLI in any phase that involves clarification questions (typically Phases 1-3):
+Use `npx ai-devkit@latest memory` CLI in any phase that involves clarification questions (typically Phases 1-3):
 
-1. **Before asking questions**: `npx ai-devkit memory search --query "<topic>"`. Apply matches; only ask about uncovered gaps.
-2. **After clarification**: `npx ai-devkit memory store --title "<title>" --content "<knowledge>" --tags "<tags>"`.
+1. **Before asking questions**: `npx ai-devkit@latest memory search --query "<topic>"`. Apply matches; only ask about uncovered gaps.
+2. **After clarification**: `npx ai-devkit@latest memory store --title "<title>" --content "<knowledge>" --tags "<tags>"`.
 
 ## Rules
 
diff --git a/skills/dev-lifecycle/scripts/check-docs.sh b/skills/dev-lifecycle/scripts/check-docs.sh
@@ -51,7 +51,7 @@ if [[ $MISSING -eq 0 ]]; then
 else
   echo "$MISSING item(s) missing."
   if [[ ! -d "$DOCS_DIR" ]]; then
-    echo "Run: npx ai-devkit init"
+    echo "Run: npx ai-devkit@latest init"
   fi
   exit 1
 fi
diff --git a/skills/memory/SKILL.md b/skills/memory/SKILL.md
@@ -19,7 +19,7 @@ Use the memory CLI commands when:
 
 Ensure AI DevKit CLI is available:
 ```bash
-npx ai-devkit --version
+npx ai-devkit@latest --version
 ```
 
 ## Commands Reference
@@ -29,7 +29,7 @@ npx ai-devkit --version
 Store new knowledge items using the `memory store` command:
 
 ```bash
-npx ai-devkit memory store \
+npx ai-devkit@latest memory store \
   --title "<short descriptive title>" \
   --content "<detailed knowledge content>" \
   --tags "<comma-separated tags>" \
@@ -49,20 +49,20 @@ npx ai-devkit memory store \
 
 ```bash
 # Store a global coding pattern
-npx ai-devkit memory store \
+npx ai-devkit@latest memory store \
   --title "Always handle BigInt serialization in API responses" \
   --content "When returning BigInt values from API endpoints, convert them to strings using \`BigInt.toString()\` before serialization. JSON.stringify() cannot serialize BigInt natively." \
   --tags "api,backend,serialization" \
   --scope "global"
 
 # Store project-specific knowledge
-npx ai-devkit memory store \
+npx ai-devkit@latest memory store \
   --title "Use pnpm for package management" \
   --content "This monorepo uses pnpm workspaces. Always use 'pnpm' instead of 'npm' or 'yarn'. Install dependencies with 'pnpm install' and run scripts with 'pnpm run <script>'." \
   --scope "project:my-monorepo"
 
 # Store repository-specific rules
-npx ai-devkit memory store \
+npx ai-devkit@latest memory store \
   --title "Database migrations require review" \
   --content "All database schema changes must be reviewed by the DBA team before merging. Create migration files in /migrations and tag the PR with 'needs-dba-review'." \
   --tags "database,migrations,process" \
@@ -74,7 +74,7 @@ npx ai-devkit memory store \
 Search for stored knowledge using the `memory search` command:
 
 ```bash
-npx ai-devkit memory search --query "<search query>"
+npx ai-devkit@latest memory search --query "<search query>"
 ```
 
 **Parameters:**
@@ -90,15 +90,15 @@ npx ai-devkit memory search --query "<search query>"
 
 ```bash
 # Basic search
-npx ai-devkit memory search --query "API response handling"
+npx ai-devkit@latest memory search --query "API response handling"
 
 # Search with tag boosting
-npx ai-devkit memory search \
+npx ai-devkit@latest memory search \
   --query "docker configuration" \
   --tags "docker,infra"
 
 # Search within a specific scope
-npx ai-devkit memory search \
+npx ai-devkit@latest memory search \
   --query "coding standards" \
   --scope "project:my-app" \
   --limit 10
@@ -158,20 +158,20 @@ When storing knowledge during a conversation:
 
 1. **Before storing**, search to avoid duplicates:
    ```bash
-   npx ai-devkit memory search --query "similar topic"
+   npx ai-devkit@latest memory search --query "similar topic"
    ```
 
 2. **After resolving an issue**, store the solution:
    ```bash
-   npx ai-devkit memory store \
+   npx ai-devkit@latest memory store \
      --title "Fix: Issue description" \
      --content "Solution details with code examples..." \
      --tags "relevant,tags"
    ```
 
 3. **Before starting a task**, search for relevant context:
    ```bash
-   npx ai-devkit memory search --query "task description"
+   npx ai-devkit@latest memory search --query "task description"
    ```
 
 ## Storage Location
diff --git a/web/app/page.tsx b/web/app/page.tsx
@@ -124,7 +124,7 @@ export default function Home() {
               </pre>
               <p className="text-gray-600 mt-6">or</p>
               <pre className="bg-black text-white p-4 rounded overflow-x-auto">
-                <code>npx ai-devkit init</code>
+                <code>npx ai-devkit@latest init</code>
               </pre>
               <p className="text-gray-600 mt-6">
                 This creates a <code>docs/ai/</code> directory with phase templates for
diff --git a/web/app/skills/page.tsx b/web/app/skills/page.tsx
@@ -72,7 +72,7 @@ export default function SkillsPage() {
 
     const handleCopy = async (skillName: string) => {
         try {
-            await navigator.clipboard.writeText(`npx ai-devkit skill add ${skillName}`);
+            await navigator.clipboard.writeText(`npx ai-devkit@latest skill add ${skillName}`);
             setCopied(true);
             setTimeout(() => setCopied(false), 2000);
         } catch {
@@ -258,7 +258,7 @@ export default function SkillsPage() {
                                     <div className="group relative">
                                         <div className="flex items-stretch rounded-xl overflow-hidden border border-gray-200 bg-gray-50">
                                             <code className="flex-1 px-4 py-4 font-mono text-sm text-gray-800 overflow-x-auto">
-                                                npx ai-devkit skill add {selectedSkill.registry} {selectedSkill.name}
+                                                npx ai-devkit@latest skill add {selectedSkill.registry} {selectedSkill.name}
                                             </code>
                                             <button
                                                 onClick={() => handleCopy(selectedSkill.registry + " " + selectedSkill.name)}
diff --git a/web/content/docs/1-getting-started.md b/web/content/docs/1-getting-started.md
@@ -39,7 +39,7 @@ npm install -g ai-devkit
 Or use it directly with npx (no installation required):
 
 ```bash
-npx ai-devkit init
+npx ai-devkit@latest init
 ```
 
 ## Initialize Your Project
diff --git a/web/content/docs/3-development-with-ai-devkit.md b/web/content/docs/3-development-with-ai-devkit.md
@@ -64,7 +64,7 @@ ai-devkit skill add codeaholicguy/ai-devkit dev-lifecycle
 or
 
 ```bash
-npx ai-devkit skill add codeaholicguy/ai-devkit dev-lifecycle
+npx ai-devkit@latest skill add codeaholicguy/ai-devkit dev-lifecycle
 ```
 
 Once installed, the skill is immediately available to your AI agent. For more details on managing skills, see [Skills](/docs/skills).
diff --git a/web/content/docs/6-memory.md b/web/content/docs/6-memory.md
@@ -14,7 +14,7 @@ The **Memory** service allows you to store actionable insights, coding patterns,
 Before using Memory, ensure you have:
 
 - **Node.js 18+** installed
-- **AI DevKit CLI** installed: `npm install -g ai-devkit` or use `npx ai-devkit`
+- **AI DevKit CLI** installed: `npm install -g ai-devkit` or use `npx ai-devkit@latest`
 - For MCP usage: A compatible AI assistant (Cursor, Claude Code, etc.)
 
 ## How It Works

Original file line number	Diff line number	Diff line change
`@@ -9,7 +9,7 @@ export function runBaseDocsRules(cwd: string, deps: LintDependencies): LintCheck`
`9`	`9`	`idPrefix: 'base',`
`10`	`10`	`category: 'base-docs',`
`11`	`11`	filePathForPhase: (phase: string) => `${DOCS_DIR}/${phase}/README.md`,
`12`		`- missingFix: 'Run: npx ai-devkit init',`
	`12`	`+ missingFix: 'Run: npx ai-devkit@latest init',`
`13`	`13`	`deps`
`14`	`14`	`});`
`15`	`15`	`}`