Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
Patterns for parallel subagent execution using the Agent tool (formerly Task).
Install Parallel Execution
$ npx skills add CloudAI-X/claude-workflow-v2 --skill parallel-execution -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install CloudAI-X/claude-workflow-v2 parallel-execution --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/CloudAI-X/claude-workflow-v2.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/parallel-execution .claude/skills/parallel-execution && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "parallel-execution" agent skill from https://github.com/CloudAI-X/claude-workflow-v2/tree/main/skills/parallel-execution into .claude/skills/parallel-execution/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "parallel-execution", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/CloudAI-X/claude-workflow-v2/tree/main/skills/parallel-executionType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add CloudAI-X/claude-workflow-v2 --skill parallel-execution -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install CloudAI-X/claude-workflow-v2 parallel-execution --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CloudAI-X/claude-workflow-v2.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/parallel-execution .agents/skills/parallel-execution && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "parallel-execution" agent skill from https://github.com/CloudAI-X/claude-workflow-v2/tree/main/skills/parallel-execution into .agents/skills/parallel-execution/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "parallel-execution", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add CloudAI-X/claude-workflow-v2 --skill parallel-execution -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install CloudAI-X/claude-workflow-v2 parallel-execution --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CloudAI-X/claude-workflow-v2.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/parallel-execution .cursor/skills/parallel-execution && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "parallel-execution" agent skill from https://github.com/CloudAI-X/claude-workflow-v2/tree/main/skills/parallel-execution into .cursor/skills/parallel-execution/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "parallel-execution", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/CloudAI-X/claude-workflow-v2.git --path skills/parallel-execution--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add CloudAI-X/claude-workflow-v2 --skill parallel-execution -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install CloudAI-X/claude-workflow-v2 parallel-execution --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CloudAI-X/claude-workflow-v2.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/parallel-execution .gemini/skills/parallel-execution && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "parallel-execution" agent skill from https://github.com/CloudAI-X/claude-workflow-v2/tree/main/skills/parallel-execution into .gemini/skills/parallel-execution/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "parallel-execution", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install CloudAI-X/claude-workflow-v2 parallel-executionInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add CloudAI-X/claude-workflow-v2 --skill parallel-execution -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/CloudAI-X/claude-workflow-v2.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/parallel-execution .github/skills/parallel-execution && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "parallel-execution" agent skill from https://github.com/CloudAI-X/claude-workflow-v2/tree/main/skills/parallel-execution into .github/skills/parallel-execution/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "parallel-execution", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add CloudAI-X/claude-workflow-v2 --skill parallel-execution -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install CloudAI-X/claude-workflow-v2 parallel-execution --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CloudAI-X/claude-workflow-v2.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/parallel-execution .opencode/skills/parallel-execution && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "parallel-execution" agent skill from https://github.com/CloudAI-X/claude-workflow-v2/tree/main/skills/parallel-execution into .opencode/skills/parallel-execution/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "parallel-execution", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
parallel-execution- GitHub stars
- 1.4k
- Token cost
- ~1.7k tokens
- SKILL.md length
- 522 words
- Files
- 1
- Skills in repo
- 13
- Repo updated
- First seen
- Licence
- MIT
At a glance
Patterns for parallel subagent execution using the Agent tool (formerly Task).
- Works in 5 steps: Identify Parallelizable Tasks → Prepare Dynamic Subagent Prompts → Launch All Tasks in ONE Message → …
- Coordinating multiple independent tasks
- SKILL.md covers Core Concept, Execution Protocol, Dynamic Subagent Patterns and Task List Integration, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Parallel Execution is an agent skill from CloudAI-X/claude-workflow-v2. Patterns for parallel subagent execution using the Agent tool (formerly Task). Use when coordinating multiple independent tasks, spawning dynamic subagents, or implementing features that can be parallelized.
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Subagents. The repository describes itself as: Universal Claude Code workflow plugin with agents, skills, hooks, and commands. The licence is MIT.
When your agent uses it
- Coordinating multiple independent tasks
- Spawning dynamic subagents
- Implementing features that can be parallelized
Example prompts
- “Use the parallel-execution skill to pattern for parallel subagent execution using the Agent tool (formerly Task)”
- “/parallel-execution”
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 3b5a89e. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Parallel Execution loads about 1.7k tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 522 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from CloudAI-X/claude-workflow-v2 at commit 3b5a89e, republished under its MIT licence (© CloudAI-X). 522 words, ~1,687 tokens.
Download SKILL.mdSave it as
.claude/skills/parallel-execution/SKILL.md (or your agent's skills folder).- name
- parallel-execution
- description
- Patterns for parallel subagent execution using the Agent tool (formerly Task). Use when coordinating multiple independent tasks, spawning dynamic subagents, or implementing features that can be parallelized.
Parallel Execution Patterns
When to Load
- Trigger: Multi-agent tasks, concurrent operations, spawning subagents, parallelizing independent work
- Skip: Single-step tasks or sequential workflows with no parallelization opportunity
Core Concept
Parallel execution spawns multiple subagents simultaneously using the Agent tool (named Task before Claude Code 2.1.63; Task still works as an alias). Subagents run in the background by default, so N tasks run concurrently, dramatically reducing total execution time.
Critical Rule: ALL Agent calls MUST be in a SINGLE assistant message for true parallelism. If the calls are in separate messages, they launch one after another.
Execution Protocol
Step 1: Identify Parallelizable Tasks
Before spawning, verify tasks are independent:
- No task depends on another's output
- Tasks target different files or concerns
- Can run simultaneously without conflicts
Step 2: Prepare Dynamic Subagent Prompts
Each subagent receives a custom prompt defining its role:
You are a [ROLE] specialist for this specific task.
Task: [CLEAR DESCRIPTION]
Context:
[RELEVANT CONTEXT ABOUT THE CODEBASE/PROJECT]
Files to work with:
[SPECIFIC FILES OR PATTERNS]
Output format:
[EXPECTED OUTPUT STRUCTURE]
Focus areas:
- [PRIORITY 1]
- [PRIORITY 2]Step 3: Launch All Tasks in ONE Message
CRITICAL: Make ALL Agent calls in the SAME assistant message:
I'm launching N parallel subagents:
[Agent 1]
description: "Subagent A - [brief purpose]"
prompt: "[detailed instructions for subagent A]"
[Agent 2]
description: "Subagent B - [brief purpose]"
prompt: "[detailed instructions for subagent B]"
[Agent 3]
description: "Subagent C - [brief purpose]"
prompt: "[detailed instructions for subagent C]"On Claude Code versions that still run subagents in the foreground by default, add run_in_background: true to each call.
Step 4: Collect Results
Each subagent returns its final result to the parent conversation automatically when it finishes. Wait until every subagent has reported before synthesizing; do not poll, and do not start dependent work early. (The separate TaskOutput call is deprecated.)
Step 5: Synthesize Results
Combine all subagent outputs into unified result:
- Merge related findings
- Resolve conflicts between recommendations
- Prioritize by severity/importance
- Create actionable summary
Dynamic Subagent Patterns
Pattern 1: Task-Based Parallelization
When you have N tasks to implement, spawn N subagents:
Plan:
1. Implement auth module
2. Create API endpoints
3. Add database schema
4. Write unit tests
5. Update documentation
Wave 1 - spawn 3 subagents (independent of each other):
- Subagent 1: Implements auth module
- Subagent 2: Creates API endpoints
- Subagent 3: Adds database schema
Wave 2 - after wave 1 has finished (these depend on its output):
- Subagent 4: Writes unit tests
- Subagent 5: Updates documentationPattern 2: Directory-Based Parallelization
Analyze multiple directories simultaneously:
Directories: src/auth, src/api, src/db
Spawn 3 subagents:
- Subagent 1: Analyzes src/auth
- Subagent 2: Analyzes src/api
- Subagent 3: Analyzes src/dbPattern 3: Perspective-Based Parallelization
Review from multiple angles simultaneously:
Perspectives: Security, Performance, Testing, Architecture
Spawn 4 subagents:
- Subagent 1: Security review
- Subagent 2: Performance analysis
- Subagent 3: Test coverage review
- Subagent 4: Architecture assessmentTask List Integration
When using parallel execution, task tracking (TaskCreate/TaskUpdate, or TodoWrite on older versions) differs:
Sequential execution: Only ONE task in_progress at a time
Parallel execution: MULTIPLE tasks can be in_progress simultaneously
# Before launching parallel tasks
todos = [
{ content: "Task A", status: "in_progress" },
{ content: "Task B", status: "in_progress" },
{ content: "Task C", status: "in_progress" },
{ content: "Synthesize results", status: "pending" }
]
# As each subagent reports back, mark its task completed
todos = [
{ content: "Task A", status: "completed" },
{ content: "Task B", status: "completed" },
{ content: "Task C", status: "completed" },
{ content: "Synthesize results", status: "in_progress" }
]Show full SKILL.md (213 more words)Show less
When to Use Parallel Execution
Good candidates:
- Multiple independent analyses (code review, security, tests)
- Multi-file processing where files are independent
- Exploratory tasks with different perspectives
- Verification tasks with different checks
- Feature implementation with independent components
Avoid parallelization when:
- Tasks have dependencies (Task B needs Task A's output)
- Sequential workflows are required (commit -> push -> PR)
- Tasks modify the same files (risk of conflicts)
- Order matters for correctness
Performance Benefits
| Approach | 5 Tasks @ 30s each | Total Time |
|---|---|---|
| Sequential | 30s + 30s + 30s + 30s + 30s | ~150s |
| Parallel | All 5 run simultaneously | ~30s |
Parallel execution is approximately Nx faster where N is the number of independent tasks.
Example: Feature Implementation
User request: "Implement user authentication with login, registration, and password reset"
Orchestrator creates plan:
- Implement login endpoint
- Implement registration endpoint
- Implement password reset endpoint
- Add authentication middleware
- Write integration tests
Parallel execution:
Wave 1 - launching 4 subagents in parallel:
[Agent 1] Login endpoint implementation
[Agent 2] Registration endpoint implementation
[Agent 3] Password reset endpoint implementation
[Agent 4] Auth middleware implementation
[Results arrive as each subagent finishes]
Wave 2 - depends on wave 1:
[Agent 5] Integration test writing
[Synthesize into cohesive implementation]Troubleshooting
Tasks running sequentially?
- Verify ALL Agent calls are in a SINGLE message
- On older Claude Code versions, check
run_in_background: trueis set for each
Results not available?
- Results are delivered when each subagent finishes; wait for all of them
- A subagent that was denied a permission may return without finishing its work; check its report
Conflicts in output?
- Ensure tasks don't modify same files
- Add conflict resolution in synthesis step
© CloudAI-X, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/parallel-execution of CloudAI-X/claude-workflow-v2.
Open the folder on GitHubat commit 3b5a89e
Compare with similar skills
Parallel Execution next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Parallel Execution this skillCloudAI-X/claude-workflow-v2 | 1.4k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Claude Code Agent Developmentanthropics/claude-plugins-official | 37k | 8 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Subagent Driven DevelopmentAsvarox/allkaraoke | 261 | 37 repos | ~1.2k | Automated safety check: Pass | None | |
| Dispatching Parallel Agentsultralisp/ultralisp | 258 | 40 repos | ~1.5k | Automated safety check: Pass | None | |
| Paseo Advisor Second Opiniongetpaseo/paseo | 20k | 1 repos | ~756 | Automated safety check: Pass | Custom licence | |
| Task Observerrebelytics/one-skill-to-rule-them-all | 3.2k | 1 repos | ~12k | Automated safety check: Pass | CC-BY-4.0 |
Similar skills
- Official
Subagent Driven Development
Asvarox/allkaraoke
A skill your agent uses when executing implementation plans with independent tasks in the current session
Dispatching Parallel Agents
ultralisp/ultralisp
A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Paseo Advisor Second Opinion
getpaseo/paseo
Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.
Task Observer
rebelytics/one-skill-to-rule-them-all
Monitors task execution for skill improvement opportunities.
O2 Review Loop
openobserve/openobserve
Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.
More from CloudAI-X/claude-workflow-v2
All 13 skills in this repoAnalyzing Projects
CloudAI-X/claude-workflow-v2
Analyzes codebases to understand structure, tech stack, patterns, and conventions.
Designing APIs
CloudAI-X/claude-workflow-v2
Designs REST and GraphQL APIs including endpoints, error handling, versioning, and documentation.
Designing Architecture
CloudAI-X/claude-workflow-v2
Designs software architecture and selects appropriate patterns for projects.
Designing Tests
CloudAI-X/claude-workflow-v2
Designs and implements testing strategies for any codebase. An agent skill from CloudAI-X/claude-workflow-v2.
Managing Git
CloudAI-X/claude-workflow-v2
Manages Git workflows including branching, commits, and pull requests.
Optimizing Performance
CloudAI-X/claude-workflow-v2
Analyzes and optimizes application performance across frontend, backend, and database layers.
Related
Categories
Questions about Parallel Execution
What does Parallel Execution do?
Patterns for parallel subagent execution using the Agent tool (formerly Task). Parallel Execution is an agent skill from CloudAI-X/claude-workflow-v2. Patterns for parallel subagent execution using the Agent tool (formerly Task).
When should I use Parallel Execution?
Parallel Execution fits situations like: coordinating multiple independent tasks; spawning dynamic subagents; implementing features that can be parallelized.
How do I install Parallel Execution in Claude Code?
Run `npx skills add CloudAI-X/claude-workflow-v2 --skill parallel-execution -a claude-code`. Or copy the skill folder (skills/parallel-execution in CloudAI-X/claude-workflow-v2) into .claude/skills/parallel-execution in your project. Claude Code loads it when a task matches its description.
How do I install Parallel Execution in Codex?
Run `npx skills add CloudAI-X/claude-workflow-v2 --skill parallel-execution -a codex`. Or copy the skill folder (skills/parallel-execution in CloudAI-X/claude-workflow-v2) into .agents/skills/parallel-execution in your project. Codex loads it when a task matches its description.
Can I use Parallel Execution in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add CloudAI-X/claude-workflow-v2 --skill parallel-execution -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/parallel-execution, .gemini/skills/parallel-execution, .github/skills/parallel-execution and .opencode/skills/parallel-execution in your project.
What does Parallel Execution need to run?
SKILL.md names no scripts, command-line tools or credentials: Parallel Execution is instructions for the agent only.
Does Parallel Execution access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Parallel Execution safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Parallel Execution use?
Parallel Execution is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Parallel Execution use?
About 1.7k tokens (SKILL.md is roughly 6.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Parallel Execution?
Skills that share tags, products or a category with Parallel Execution: Claude Code Agent Development (anthropics/claude-plugins-official, 37k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Parallel Execution?
CloudAI-X (a GitHub user) maintains it in CloudAI-X/claude-workflow-v2, which has 1,418 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 6, 2026.
Source: CloudAI-X/claude-workflow-v2 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.