agentsys 5.0.1 → 5.0.3

package/.claude-plugin/marketplace.json

@@ -1,7 +1,7 @@
 {
   "name": "agentsys",
   "description": "12 specialized plugins for AI workflow automation - task orchestration, PR workflow, slop detection, code review, drift detection, enhancement analysis, documentation sync, repo mapping, perf investigations, topic research, agent config linting, and cross-tool AI consultation",
-  "version": "5.0.1",
+  "version": "5.0.3",
   "owner": {
     "name": "Avi Fenesh",
     "url": "https://github.com/avifenesh"
@@ -26,84 +26,84 @@
       "name": "next-task",
       "source": "./plugins/next-task",
       "description": "Master workflow orchestrator: autonomous workflow with model optimization (opus/sonnet/haiku), two-file state management, workflow enforcement gates, 14 specialist agents",
-      "version": "5.0.1",
+      "version": "5.0.3",
       "category": "productivity"
     },
     {
       "name": "ship",
       "source": "./plugins/ship",
       "description": "Complete PR workflow: commit to production, skips review when called from next-task, removes task from registry on cleanup, automatic rollback",
-      "version": "5.0.1",
+      "version": "5.0.3",
       "category": "deployment"
     },
     {
       "name": "deslop",
       "source": "./plugins/deslop",
       "description": "3-phase AI slop detection: regex patterns (HIGH), multi-pass analyzers (MEDIUM), CLI tools (LOW)",
-      "version": "5.0.1",
+      "version": "5.0.3",
       "category": "development"
     },
     {
       "name": "audit-project",
       "source": "./plugins/audit-project",
       "description": "Multi-agent iterative code review until zero issues remain",
-      "version": "5.0.1",
+      "version": "5.0.3",
       "category": "development"
     },
     {
       "name": "drift-detect",
       "source": "./plugins/drift-detect",
       "description": "Deep repository analysis to realign project plans with code reality - detects drift, gaps, and creates prioritized reconstruction plans",
-      "version": "5.0.1",
+      "version": "5.0.3",
       "category": "productivity"
     },
     {
       "name": "enhance",
       "source": "./plugins/enhance",
       "description": "Master enhancement orchestrator: parallel analyzer execution for plugins, agents, docs, CLAUDE.md, and prompts with unified reporting",
-      "version": "5.0.1",
+      "version": "5.0.3",
       "category": "development"
     },
     {
       "name": "sync-docs",
       "source": "./plugins/sync-docs",
       "description": "Standalone documentation sync: find outdated refs, update CHANGELOG, flag stale examples based on code changes",
-      "version": "5.0.1",
+      "version": "5.0.3",
       "category": "development"
     },
     {
       "name": "repo-map",
       "source": "./plugins/repo-map",
       "description": "AST-based repository map generation using ast-grep with incremental updates for faster drift analysis",
-      "version": "5.0.1",
+      "version": "5.0.3",
       "category": "development"
     },
     {
       "name": "perf",
       "source": "./plugins/perf",
       "description": "Rigorous performance investigation workflow with baselines, profiling, hypotheses, and evidence-backed decisions",
-      "version": "5.0.1",
+      "version": "5.0.3",
       "category": "development"
     },
     {
       "name": "learn",
       "source": "./plugins/learn",
       "description": "Research topics online and create comprehensive learning guides with RAG-optimized indexes",
-      "version": "5.0.1",
+      "version": "5.0.3",
       "category": "productivity"
     },
     {
       "name": "agnix",
       "source": "./plugins/agnix",
       "description": "Lint agent configuration files (SKILL.md, CLAUDE.md, hooks, MCP) against 155 rules across 10+ AI tools",
-      "version": "5.0.1",
+      "version": "5.0.3",
       "category": "development"
     },
     {
       "name": "consult",
       "source": "./plugins/consult",
       "description": "Cross-tool AI consultation: get second opinions from Gemini CLI, Codex CLI, Claude Code, OpenCode, or Copilot CLI with model and thinking effort control",
-      "version": "5.0.1",
+      "version": "5.0.3",
       "category": "productivity"
     }
   ]

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "agentsys",
-  "version": "5.0.1",
+  "version": "5.0.3",
   "description": "Professional-grade slash commands for Claude Code with cross-platform support",
   "keywords": [
     "workflow",

package/CHANGELOG.md

@@ -9,6 +9,16 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [5.0.3] - 2026-02-17
+
+### Fixed
+- **Consult: Codex command corrected to `codex exec`** - Codex CLI uses `codex exec` for non-interactive mode (not `-q` flag). Non-interactive resume uses `codex exec resume SESSION_ID "prompt" --json`. All four tools (Claude, Gemini, Codex, OpenCode) now have correct native session resume support.
+
+## [5.0.2] - 2026-02-17
+
+### Fixed
+- **Consult: Codex and OpenCode marked as continuable** - Both tools support session resume but were incorrectly marked as non-continuable. OpenCode supports `--session SESSION_ID` and `--continue` flags in non-interactive mode.
+
 ## [5.0.1] - 2026-02-14
 
 ### Fixed

package/README.md

@@ -17,6 +17,7 @@
   <a href="https://github.com/avifenesh/agentsys/stargazers"><img src="https://img.shields.io/github/stars/avifenesh/agentsys?style=social" alt="GitHub stars"></a>
   <a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="License: MIT"></a>
   <a href="https://avifenesh.github.io/agentsys/"><img src="https://img.shields.io/badge/Website-AgentSys-blue?style=flat&logo=github" alt="Website"></a>
+  <a href="https://github.com/hesreallyhim/awesome-claude-code"><img src="https://awesome.re/mentioned-badge.svg" alt="Mentioned in Awesome Claude Code"></a>
 </p>
 
 <p align="center">

package/adapters/codex/skills/consult/SKILL.md

@@ -209,9 +209,9 @@ The results of the consultation are:
 {response}
 ```
 
-For continuable tools (Claude/Gemini), also display: `Session: {session_id} - use /consult --continue to resume`
+For continuable tools (Claude, Gemini, Codex, OpenCode), display: `Session: {session_id} - use /consult --continue to resume`
 
-Save session state for continuable tools (Claude, Gemini) to `{AI_STATE_DIR}/consult/last-session.json`.
+Save session state for continuable tools (Claude, Gemini, Codex, OpenCode) to `{AI_STATE_DIR}/consult/last-session.json`.
 
 Platform state directory:
 - Claude Code: `.claude/`

package/adapters/opencode/agents/consult-agent.md

@@ -75,7 +75,7 @@ The results of the consultation are:
 {response}
 ```
 
-Set `continuable: true` only for Claude and Gemini (tools with session resumption support).
+Set `continuable: true` for Claude, Gemini, Codex, and OpenCode (tools with session resume support). Only Copilot is non-continuable. Each tool uses a different resume mechanism: Claude/Gemini use `--resume`, Codex uses `codex exec resume`, OpenCode uses `--session`/`--continue`.
 
 ### 5. Save Session State
 

package/adapters/opencode/commands/consult.md

@@ -216,9 +216,9 @@ The results of the consultation are:
 {response}
 ```
 
-For continuable tools (Claude/Gemini), also display: `Session: {session_id} - use /consult --continue to resume`
+For continuable tools (Claude, Gemini, Codex, OpenCode), display: `Session: {session_id} - use /consult --continue to resume`
 
-Save session state for continuable tools (Claude, Gemini) to `{AI_STATE_DIR}/consult/last-session.json`.
+Save session state for continuable tools (Claude, Gemini, Codex, OpenCode) to `{AI_STATE_DIR}/consult/last-session.json`.
 
 Platform state directory:
 - Claude Code: `.opencode/`

package/adapters/opencode/skills/agnix/SKILL.md

@@ -2,7 +2,7 @@
 ---
 name: agnix
 description: "Use when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'. Validates agent configuration files against 155 rules across 10+ AI tools."
-version: 5.0.1
+version: 5.0.3
 argument-hint: "[path] [--fix] [--strict] [--target=claude-code|cursor|codex]"
 ---
 

package/adapters/opencode/skills/consult/SKILL.md

@@ -2,7 +2,7 @@
 ---
 name: consult
 description: "Cross-tool AI consultation. Use when user asks to 'consult gemini', 'ask codex', 'get second opinion', 'cross-check with claude', 'consult another AI', 'ask opencode', 'copilot opinion', or wants a second opinion from a different AI tool."
-version: 5.0.1
+version: 5.0.3
 argument-hint: "[question] [--tool] [--effort] [--model] [--context] [--continue]"
 ---
 
@@ -82,9 +82,13 @@ Models: gemini-2.5-flash, gemini-2.5-pro, gemini-3-flash-preview, gemini-3-pro-p
 ### Codex
 
 ```
-Command: codex -q "QUESTION" --json -m "MODEL" -a suggest -c model_reasoning_effort="LEVEL"
+Command: codex exec "QUESTION" --json -m "MODEL" -a suggest -c model_reasoning_effort="LEVEL"
+Session resume: codex exec resume SESSION_ID "QUESTION" --json
+Session resume (latest): codex exec resume --last "QUESTION" --json
 ```
 
+Note: `codex exec` is the non-interactive/headless mode. There is no `-q` flag. The TUI mode is `codex` (no subcommand).
+
 Models: gpt-5.1-codex-mini, gpt-5-codex, gpt-5.1-codex, gpt-5.2-codex, gpt-5.3-codex, gpt-5.1-codex-max
 
 | Effort | Model | Reasoning |
@@ -95,12 +99,14 @@ Models: gpt-5.1-codex-mini, gpt-5-codex, gpt-5.1-codex, gpt-5.2-codex, gpt-5.3-c
 | max | gpt-5.3-codex | xhigh |
 
 **Parse output**: `JSON.parse(stdout).message` or raw text
-**Continuable**: No
+**Session ID**: Codex prints a resume hint at session end (e.g., `codex resume SESSION_ID`). Extract the session ID from stdout or from `JSON.parse(stdout).session_id` if available.
+**Continuable**: Yes. Sessions are stored as JSONL rollout files at `~/.codex/sessions/`. Non-interactive resume uses `codex exec resume SESSION_ID "follow-up prompt" --json`. Use `--last` instead of a session ID to resume the most recent session.
 
 ### OpenCode
 
 ```
 Command: opencode run "QUESTION" --format json --model "MODEL" --variant "VARIANT"
+Session resume: opencode run "QUESTION" --format json --model "MODEL" --variant "VARIANT" --continue (most recent) or --session "SESSION_ID"
 With thinking: add --thinking flag
 ```
 
@@ -114,7 +120,8 @@ Models: 75+ via providers (format: provider/model). Top picks: claude-sonnet-4-5
 | max | (user-selected or default) | high + --thinking |
 
 **Parse output**: Parse JSON events from stdout, extract final text response
-**Continuable**: No
+**Session ID**: Extract from JSON output if available, or use `--continue` to auto-resume the most recent session.
+**Continuable**: Yes (via `--continue` or `--session`). Sessions are stored in a SQLite database in the OpenCode data directory. Use `--session SESSION_ID` for a specific session, or `--continue` for the most recent.
 
 ### Copilot
 
@@ -156,7 +163,10 @@ If `--model` is specified, use it directly. Otherwise, use the effort-based mode
 
 Use the command template from the provider's configuration section. Substitute QUESTION, MODEL, TURNS, LEVEL, and VARIANT with resolved values.
 
-If continuing a session (Claude or Gemini): append `--resume SESSION_ID`.
+If continuing a session:
+- **Claude or Gemini**: append `--resume SESSION_ID` to the command.
+- **Codex**: use `codex exec resume SESSION_ID "QUESTION" --json` instead of the standard command. Use `--last` instead of a session ID for the most recent session.
+- **OpenCode**: append `--session SESSION_ID` to the command. If no session_id is saved, use `--continue` instead (resumes most recent session).
 If OpenCode at max effort: append `--thinking`.
 
 ### Step 3: Context Packaging
@@ -181,9 +191,15 @@ User-provided question text MUST NOT be interpolated into shell command strings.
 | Provider | Safe command pattern |
 |----------|---------------------|
 | Claude | `claude -p - --output-format json --model "MODEL" --max-turns TURNS --allowedTools "Read,Glob,Grep" < "{AI_STATE_DIR}/consult/question.tmp"` |
+| Claude (resume) | `claude -p - --output-format json --model "MODEL" --max-turns TURNS --allowedTools "Read,Glob,Grep" --resume "SESSION_ID" < "{AI_STATE_DIR}/consult/question.tmp"` |
 | Gemini | `gemini -p - --output-format json -m "MODEL" < "{AI_STATE_DIR}/consult/question.tmp"` |
-| Codex | `codex -q "$(cat "{AI_STATE_DIR}/consult/question.tmp")" --json -m "MODEL" -a suggest` (Codex lacks stdin mode -- cat reads from platform-controlled path, not user input) |
+| Gemini (resume) | `gemini -p - --output-format json -m "MODEL" --resume "SESSION_ID" < "{AI_STATE_DIR}/consult/question.tmp"` |
+| Codex | `codex exec "$(cat "{AI_STATE_DIR}/consult/question.tmp")" --json -m "MODEL" -a suggest` (Codex exec lacks stdin mode -- cat reads from platform-controlled path, not user input) |
+| Codex (resume) | `codex exec resume SESSION_ID "$(cat "{AI_STATE_DIR}/consult/question.tmp")" --json -m "MODEL"` |
+| Codex (resume latest) | `codex exec resume --last "$(cat "{AI_STATE_DIR}/consult/question.tmp")" --json -m "MODEL"` |
 | OpenCode | `opencode run - --format json --model "MODEL" --variant "VARIANT" < "{AI_STATE_DIR}/consult/question.tmp"` |
+| OpenCode (resume by ID) | `opencode run - --format json --model "MODEL" --variant "VARIANT" --session "SESSION_ID" < "{AI_STATE_DIR}/consult/question.tmp"` |
+| OpenCode (resume latest) | `opencode run - --format json --model "MODEL" --variant "VARIANT" --continue < "{AI_STATE_DIR}/consult/question.tmp"` |
 | Copilot | `copilot -p - < "{AI_STATE_DIR}/consult/question.tmp"` |
 
 3. **Delete the temp file** after the command completes (success or failure). Always clean up to prevent accumulation.

package/adapters/opencode/skills/deslop/SKILL.md

@@ -2,7 +2,7 @@
 ---
 name: deslop
 description: "Use when user wants to clean AI slop from code. Use for cleanup, remove debug statements, find ghost code, repo hygiene."
-version: 5.0.1
+version: 5.0.3
 argument-hint: "[report|apply] [--scope=all|diff|path] [--thoroughness=quick|normal|deep]"
 ---
 

package/adapters/opencode/skills/discover-tasks/SKILL.md

@@ -2,7 +2,7 @@
 ---
 name: discover-tasks
 description: "Use when user asks to \"discover tasks\", \"find next task\", or \"prioritize issues\". Discovers and ranks tasks from GitHub, GitLab, local files, and custom sources."
-version: 5.0.1
+version: 5.0.3
 ---
 
 # discover-tasks

package/adapters/opencode/skills/drift-analysis/SKILL.md

@@ -2,7 +2,7 @@
 ---
 name: drift-analysis
 description: Use when the user asks about plan drift, reality check, comparing docs to code, project state analysis, roadmap alignment, implementation gaps, or needs guidance on identifying discrepancies between documented plans and actual implementation state.
-version: 5.0.1
+version: 5.0.3
 ---
 
 # Drift Analysis

package/adapters/opencode/skills/enhance-agent-prompts/SKILL.md

@@ -2,7 +2,7 @@
 ---
 name: enhance-agent-prompts
 description: "Use when improving agent prompts, frontmatter, and tool restrictions."
-version: 5.0.1
+version: 5.0.3
 argument-hint: "[path] [--fix] [--verbose]"
 ---
 

package/adapters/opencode/skills/enhance-claude-memory/SKILL.md

@@ -2,7 +2,7 @@
 ---
 name: enhance-claude-memory
 description: "Use when improving CLAUDE.md or AGENTS.md project memory files."
-version: 5.0.1
+version: 5.0.3
 ---
 
 > **OpenCode Note**: Invoke agents using `@agent-name` syntax.

package/adapters/opencode/skills/enhance-cross-file/SKILL.md

@@ -2,7 +2,7 @@
 ---
 name: enhance-cross-file
 description: "Use when checking cross-file consistency: tools vs frontmatter, agent references, duplicate rules, contradictions."
-version: 5.0.1
+version: 5.0.3
 argument-hint: "[path]"
 ---
 

package/adapters/opencode/skills/enhance-docs/SKILL.md

@@ -2,7 +2,7 @@
 ---
 name: enhance-docs
 description: "Use when improving documentation structure, accuracy, and RAG readiness."
-version: 5.0.1
+version: 5.0.3
 argument-hint: "[path] [--fix] [--ai]"
 ---
 

package/adapters/opencode/skills/enhance-hooks/SKILL.md

@@ -2,7 +2,7 @@
 ---
 name: enhance-hooks
 description: "Use when reviewing hooks for safety, timeouts, and correct frontmatter."
-version: 5.0.1
+version: 5.0.3
 argument-hint: "[path] [--fix]"
 ---
 

package/adapters/opencode/skills/enhance-orchestrator/SKILL.md

@@ -2,7 +2,7 @@
 ---
 name: enhance-orchestrator
 description: "Use when coordinating multiple enhancers for /enhance command. Runs analyzers in parallel and produces unified report."
-version: 5.0.1
+version: 5.0.3
 argument-hint: "[path] [--apply] [--focus=TYPE]"
 ---
 

package/adapters/opencode/skills/enhance-plugins/SKILL.md

@@ -2,7 +2,7 @@
 ---
 name: enhance-plugins
 description: "Use when analyzing plugin structures, MCP tools, and plugin security patterns."
-version: 5.0.1
+version: 5.0.3
 argument-hint: "[path] [--fix]"
 ---
 

package/adapters/opencode/skills/enhance-prompts/SKILL.md

@@ -2,7 +2,7 @@
 ---
 name: enhance-prompts
 description: "Use when improving general prompts for structure, examples, and constraints."
-version: 5.0.1
+version: 5.0.3
 argument-hint: "[path] [--fix]"
 ---
 

package/adapters/opencode/skills/enhance-skills/SKILL.md

@@ -2,7 +2,7 @@
 ---
 name: enhance-skills
 description: "Use when reviewing SKILL.md files for structure and trigger quality."
-version: 5.0.1
+version: 5.0.3
 argument-hint: "[path] [--fix]"
 ---
 

package/adapters/opencode/skills/learn/SKILL.md

@@ -2,7 +2,7 @@
 ---
 name: learn
 description: "Research any topic online and create learning guides. Use when user asks to 'learn about', 'research topic', 'create learning guide', 'build knowledge base', or 'study subject'."
-version: 5.0.1
+version: 5.0.3
 argument-hint: "[topic] [--depth=brief|medium|deep]"
 ---
 

package/adapters/opencode/skills/perf-analyzer/SKILL.md

@@ -2,7 +2,7 @@
 ---
 name: perf-analyzer
 description: "Use when synthesizing perf findings into evidence-backed recommendations and decisions."
-version: 5.0.1
+version: 5.0.3
 ---
 
 # perf-analyzer

package/adapters/opencode/skills/perf-baseline-manager/SKILL.md

@@ -2,7 +2,7 @@
 ---
 name: perf-baseline-manager
 description: "Use when managing perf baselines, consolidating results, or comparing versions. Ensures one baseline JSON per version."
-version: 5.0.1
+version: 5.0.3
 ---
 
 # perf-baseline-manager

package/adapters/opencode/skills/perf-benchmarker/SKILL.md

@@ -2,7 +2,7 @@
 ---
 name: perf-benchmarker
 description: "Use when running performance benchmarks, establishing baselines, or validating regressions with sequential runs. Enforces 60s minimum runs (30s only for binary search) and no parallel benchmarks."
-version: 5.0.1
+version: 5.0.3
 argument-hint: "[command] [duration]"
 ---
 

package/adapters/opencode/skills/perf-code-paths/SKILL.md

@@ -2,7 +2,7 @@
 ---
 name: perf-code-paths
 description: "Use when mapping code paths, entrypoints, and likely hot files before profiling."
-version: 5.0.1
+version: 5.0.3
 ---
 
 # perf-code-paths

package/adapters/opencode/skills/perf-investigation-logger/SKILL.md

@@ -2,7 +2,7 @@
 ---
 name: perf-investigation-logger
 description: "Use when appending structured perf investigation notes and evidence."
-version: 5.0.1
+version: 5.0.3
 ---
 
 # perf-investigation-logger

package/adapters/opencode/skills/perf-profiler/SKILL.md

@@ -2,7 +2,7 @@
 ---
 name: perf-profiler
 description: "Use when profiling CPU/memory hot paths, generating flame graphs, or capturing JFR/perf evidence."
-version: 5.0.1
+version: 5.0.3
 argument-hint: "[tool] [command]"
 ---
 

package/adapters/opencode/skills/perf-theory-gatherer/SKILL.md

@@ -2,7 +2,7 @@
 ---
 name: perf-theory-gatherer
 description: "Use when generating performance hypotheses backed by git history and code evidence."
-version: 5.0.1
+version: 5.0.3
 ---
 
 # perf-theory-gatherer

package/adapters/opencode/skills/perf-theory-tester/SKILL.md

@@ -2,7 +2,7 @@
 ---
 name: perf-theory-tester
 description: "Use when running controlled perf experiments to validate hypotheses."
-version: 5.0.1
+version: 5.0.3
 ---
 
 # perf-theory-tester

package/adapters/opencode/skills/sync-docs/SKILL.md

@@ -2,7 +2,7 @@
 ---
 name: sync-docs
 description: "Sync documentation with code. Use when user asks to update docs, check docs, fix stale documentation, update changelog, or after code changes."
-version: 5.0.1
+version: 5.0.3
 argument-hint: "[report|apply] [--scope=all|recent|before-pr] [--include-undocumented]"
 allowed-tools: Bash(git:*), Read, Grep, Glob
 ---

package/adapters/opencode/skills/validate-delivery/SKILL.md

@@ -2,7 +2,7 @@
 ---
 name: validate-delivery
 description: "Use when user asks to \"validate delivery\", \"check readiness\", or \"verify completion\". Runs tests, build, and requirement checks with pass/fail instructions."
-version: 5.0.1
+version: 5.0.3
 ---
 
 # validate-delivery

package/bin/cli.js

@@ -214,6 +214,7 @@ function installForClaude() {
 
     // Discover plugins from filesystem convention
     const plugins = discovery.discoverPlugins(PACKAGE_DIR);
+    const failedPlugins = [];
     for (const plugin of plugins) {
       // Validate plugin name before shell use (prevents injection)
       if (!/^[a-z0-9][a-z0-9-]*$/.test(plugin)) continue;
@@ -232,11 +233,17 @@ function installForClaude() {
         try {
           execSync(`claude plugin update ${plugin}@agentsys`, { stdio: 'pipe' });
         } catch {
-          // Ignore if update also fails
+          failedPlugins.push(plugin);
         }
       }
     }
 
+    if (failedPlugins.length > 0) {
+      console.log(`\n[ERROR] Failed to install/update ${failedPlugins.length} plugin(s): ${failedPlugins.join(', ')}`);
+      console.log('Retry with: /plugin install <plugin>@agentsys');
+      return false;
+    }
+
     console.log('\n[OK] Claude Code installation complete!\n');
     console.log('Commands: ' + plugins.map(p => '/' + p).join(', '));
     return true;
@@ -696,24 +703,36 @@ async function main() {
   }
 
   // Install for each platform
+  const failedPlatforms = [];
   for (const platform of selected) {
     switch (platform) {
       case 'claude':
-        if (args.development) {
-          installForClaudeDevelopment();
+        if (args.development && !installForClaudeDevelopment()) {
+          failedPlatforms.push('claude');
         } else {
-          installForClaude();
+          if (!args.development && !installForClaude()) {
+            failedPlatforms.push('claude');
+          }
         }
         break;
       case 'opencode':
-        installForOpenCode(installDir, { stripModels: args.stripModels });
+        if (!installForOpenCode(installDir, { stripModels: args.stripModels })) {
+          failedPlatforms.push('opencode');
+        }
         break;
       case 'codex':
-        installForCodex(installDir);
+        if (!installForCodex(installDir)) {
+          failedPlatforms.push('codex');
+        }
         break;
     }
   }
 
+  if (failedPlatforms.length > 0) {
+    console.log(`\n[ERROR] Installation failed for: ${failedPlatforms.join(', ')}`);
+    process.exitCode = 1;
+  }
+
   console.log('─'.repeat(45));
   if (installDir) {
     console.log(`\nInstallation directory: ${installDir}`);

package/bin/dev-cli.js

@@ -13,7 +13,8 @@
  */
 
 const path = require('path');
-const { execSync } = require('child_process');
+const { execSync, spawnSync } = require('child_process');
+const { resolveExecutableForPlatform } = require('../lib/utils/command-parser');
 
 const VERSION = require('../package.json').version;
 const ROOT_DIR = path.join(__dirname, '..');
@@ -293,13 +294,22 @@ const COMMANDS = {
     description: 'Run test suite',
     handler: (args) => {
       try {
-        const cmd = ['npm', 'test'];
+        const cmdArgs = ['test'];
         if (args.length > 0) {
-          cmd.push('--');
-          cmd.push(...args);
+          cmdArgs.push('--');
+          cmdArgs.push(...args);
         }
-        execSync(cmd.join(' '), { cwd: ROOT_DIR, stdio: 'inherit' });
-        return 0;
+        const npmExecutable = resolveExecutableForPlatform('npm');
+        const result = spawnSync(npmExecutable, cmdArgs, {
+          cwd: ROOT_DIR,
+          stdio: 'inherit',
+          shell: false,
+          windowsHide: true
+        });
+        if (result.error) {
+          throw result.error;
+        }
+        return typeof result.status === 'number' ? result.status : 1;
       } catch (err) {
         return err.status || 1;
       }