aiskillstore/marketplace / skills/4eyedengineer/orchestrating-parallel-agents
orchestrating-parallel-agents
VerifiedSpawns multiple AI coding agents to work on related GitHub issues concurrently using git worktrees. Use when breaking down a large feature into multiple issues, running parallel agents with --print flag, or managing wave-based execution of related tasks.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.5 KB |
| skill-report.json | config | 26.8 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-04T16:53:19.907Z",
"slug": "4eyedengineer-orchestrating-parallel-agents",
"source_url": "https://github.com/4eyedengineer/4eyed_development/tree/main/.claude/skills/orchestrating-parallel-agents",
"source_ref": "main",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "9533951c6e12888c4ab96cf40ddf829b1ba016838e74be82749ad0fbc20323b1",
"tree_hash": "c6cf1ba0500dc8b162b663bf57ad13b5b42b24bc2f8992a33bea71cb259e3582",
"provenance": {
"model_effective": "codex",
"fallback_chain": [
{
"agent": "codex",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
}
},
"skill": {
"name": "orchestrating-parallel-agents",
"description": "Guides teams through splitting large coding work into GitHub issues, launching parallel AI agents with git worktrees, and merging results safely.",
"summary": "Coordinate parallel AI coding agents with issue prompts, git worktrees, staged waves, monitoring, and merge cleanup.",
"icon": "📦",
"version": "1.0.1",
"author": "4eyedengineer",
"license": "MIT",
"tags": [
"parallel-agents",
"git-worktrees",
"github-issues",
"agent-orchestration",
"claude-cli"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"external_commands"
],
"category": "coding"
},
"security_audit": {
"risk_level": "medium",
"is_blocked": false,
"safe_to_publish": true,
"analysis_status": "ok",
"summary": "The static Ruby backtick findings are Markdown fences, inline code, or documented command examples rather than executable Ruby code. No prompt injection was found in SKILL.md. The main security concern is explicit guidance to pre-approve git add, commit, and push for non-interactive agents.",
"remediation": [
{
"issue": "Overbroad git command pre-approval",
"suggestion": "Narrow settings.local.json permissions to exact worktree paths and branch names, and require confirmation before push operations.",
"severity": "medium"
},
{
"issue": "Non-interactive agents can publish incorrect changes",
"suggestion": "Require manual diff review before commit and push, and keep branch protection on shared repositories.",
"severity": "medium"
},
{
"issue": "Parallel wave size is not bounded",
"suggestion": "Add dry-run guidance and a recommended maximum wave size before production use.",
"severity": "low"
}
],
"risk_factor_evidence": [
{
"factor": "external_commands",
"evidence": [
{
"file": "SKILL.md",
"line_start": 22,
"line_end": 32
},
{
"file": "SKILL.md",
"line_start": 32,
"line_end": 38
},
{
"file": "SKILL.md",
"line_start": 38,
"line_end": 46
},
{
"file": "SKILL.md",
"line_start": 46,
"line_end": 53
},
{
"file": "SKILL.md",
"line_start": 53,
"line_end": 59
},
{
"file": "SKILL.md",
"line_start": 59,
"line_end": 63
},
{
"file": "SKILL.md",
"line_start": 63,
"line_end": 69
},
{
"file": "SKILL.md",
"line_start": 69,
"line_end": 69
},
{
"file": "SKILL.md",
"line_start": 71,
"line_end": 75
},
{
"file": "SKILL.md",
"line_start": 75,
"line_end": 79
},
{
"file": "SKILL.md",
"line_start": 79,
"line_end": 83
},
{
"file": "SKILL.md",
"line_start": 83,
"line_end": 87
},
{
"file": "SKILL.md",
"line_start": 87,
"line_end": 91
},
{
"file": "SKILL.md",
"line_start": 91,
"line_end": 97
},
{
"file": "SKILL.md",
"line_start": 97,
"line_end": 102
},
{
"file": "SKILL.md",
"line_start": 102,
"line_end": 106
},
{
"file": "SKILL.md",
"line_start": 106,
"line_end": 108
},
{
"file": "SKILL.md",
"line_start": 108,
"line_end": 112
},
{
"file": "SKILL.md",
"line_start": 112,
"line_end": 116
},
{
"file": "SKILL.md",
"line_start": 116,
"line_end": 120
},
{
"file": "SKILL.md",
"line_start": 120,
"line_end": 124
}
]
}
],
"static_findings": [
{
"id": "external_commands:SKILL.md:22:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 22,
"line_end": 32,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:32:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 32,
"line_end": 38,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:38:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 38,
"line_end": 46,
"snippet": "```markdown"
},
{
"id": "external_commands:SKILL.md:46:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 46,
"line_end": 53,
"snippet": "- `path/to/file` - what changes"
},
{
"id": "external_commands:SKILL.md:53:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 53,
"line_end": 59,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:59:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 59,
"line_end": 63,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:63:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 63,
"line_end": 69,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:69:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 69,
"line_end": 69,
"snippet": "Add to `.claude/settings.local.json` for non-interactive `--print` mode:"
},
{
"id": "external_commands:SKILL.md:71:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 71,
"line_end": 75,
"snippet": "```json"
},
{
"id": "external_commands:SKILL.md:75:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 75,
"line_end": 79,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:79:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 79,
"line_end": 83,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:83:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 83,
"line_end": 87,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:87:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 87,
"line_end": 91,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:91:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 91,
"line_end": 97,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:97:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 97,
"line_end": 102,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:102:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 102,
"line_end": 106,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:106:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 106,
"line_end": 108,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:108:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 108,
"line_end": 112,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:112:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 112,
"line_end": 116,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:116:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 116,
"line_end": 120,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:120:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 120,
"line_end": 124,
"snippet": "```bash"
},
{
"id": "blocker:SKILL.md:28:network-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "Network reconnaissance",
"file": "SKILL.md",
"line_start": 28,
"line_end": 29,
"snippet": "- [ ] 5. Monitor progress"
}
],
"finding_verdicts": [
{
"id": "external_commands:SKILL.md:22:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The matched text is Markdown formatting or template prose, not Ruby backtick execution. It is documentation content rather than runnable skill code."
},
{
"id": "external_commands:SKILL.md:32:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The matched text is Markdown formatting or template prose, not Ruby backtick execution. It is documentation content rather than runnable skill code."
},
{
"id": "external_commands:SKILL.md:38:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The matched text is Markdown formatting or template prose, not Ruby backtick execution. It is documentation content rather than runnable skill code."
},
{
"id": "external_commands:SKILL.md:46:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 46 is an inline Markdown placeholder for a file path in an issue template. It is not executable code or shell interpolation."
},
{
"id": "external_commands:SKILL.md:53:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The matched text is Markdown formatting or template prose, not Ruby backtick execution. It is documentation content rather than runnable skill code."
},
{
"id": "external_commands:SKILL.md:59:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The matched text is Markdown formatting or template prose, not Ruby backtick execution. It is documentation content rather than runnable skill code."
},
{
"id": "external_commands:SKILL.md:63:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The matched text is Markdown formatting or template prose, not Ruby backtick execution. It is documentation content rather than runnable skill code."
},
{
"id": "external_commands:SKILL.md:69:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "Line 69 contains inline Markdown references to settings.local.json and --print, not a Ruby shell backtick. It documents a configuration step."
},
{
"id": "external_commands:SKILL.md:71:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.94,
"reason": "The lines are a fenced JSON snippet containing Claude permission strings, not Ruby backtick execution. The broader permission risk is captured as a semantic finding."
},
{
"id": "external_commands:SKILL.md:75:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The matched text is Markdown formatting or template prose, not Ruby backtick execution. It is documentation content rather than runnable skill code."
},
{
"id": "external_commands:SKILL.md:79:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The lines are fenced Markdown shell examples, not code executed by installing the skill. The documented command workflow is reviewed separately as semantic context."
},
{
"id": "external_commands:SKILL.md:83:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The matched text is Markdown formatting or template prose, not Ruby backtick execution. It is documentation content rather than runnable skill code."
},
{
"id": "external_commands:SKILL.md:87:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The lines are fenced Markdown shell examples, not code executed by installing the skill. The documented command workflow is reviewed separately as semantic context."
},
{
"id": "external_commands:SKILL.md:91:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The matched text is Markdown formatting or template prose, not Ruby backtick execution. It is documentation content rather than runnable skill code."
},
{
"id": "external_commands:SKILL.md:97:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The lines are fenced Markdown shell examples, not code executed by installing the skill. The documented command workflow is reviewed separately as semantic context."
},
{
"id": "external_commands:SKILL.md:102:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The matched text is Markdown formatting or template prose, not Ruby backtick execution. It is documentation content rather than runnable skill code."
},
{
"id": "external_commands:SKILL.md:106:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The lines are fenced Markdown shell examples, not code executed by installing the skill. The documented command workflow is reviewed separately as semantic context."
},
{
"id": "external_commands:SKILL.md:108:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The matched text is Markdown formatting or template prose, not Ruby backtick execution. It is documentation content rather than runnable skill code."
},
{
"id": "external_commands:SKILL.md:112:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The lines are fenced Markdown shell examples, not code executed by installing the skill. The documented command workflow is reviewed separately as semantic context."
},
{
"id": "external_commands:SKILL.md:116:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The matched text is Markdown formatting or template prose, not Ruby backtick execution. It is documentation content rather than runnable skill code."
},
{
"id": "external_commands:SKILL.md:120:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The lines are fenced Markdown shell examples, not code executed by installing the skill. The documented command workflow is reviewed separately as semantic context."
},
{
"id": "blocker:SKILL.md:28:network-reconnaissance",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "Lines 28-29 are checklist text about monitoring agent progress, not network reconnaissance. No scanning target, network command, or discovery behavior appears there."
}
],
"semantic_findings": [
{
"title": "Broad Git Command Pre-Approval",
"description": "The skill instructs users to permit non-interactive agents to run git add, commit, and push through Claude settings. This can publish unintended repository changes if issue prompts or agent behavior are wrong.",
"severity": "medium",
"locations": [
{
"file": "SKILL.md",
"line_start": 67,
"line_end": 75
},
{
"file": "SKILL.md",
"line_start": 79,
"line_end": 82
}
],
"confidence": 0.86,
"confidence_reasoning": "Lines 69-75 directly grant git mutation commands for --print mode, and lines 79-82 launch background agents. This is intentional workflow behavior, not a scanner artifact."
}
],
"critical_findings": [],
"high_findings": [],
"medium_findings": [
{
"title": "Broad Git Command Pre-Approval",
"description": "The skill instructs users to permit non-interactive agents to run git add, commit, and push through Claude settings. This can publish unintended repository changes if issue prompts or agent behavior are wrong.",
"locations": [
{
"file": "SKILL.md",
"line_start": 67,
"line_end": 75
},
{
"file": "SKILL.md",
"line_start": 79,
"line_end": 82
}
],
"review_kind": "security",
"source_category": "semantic",
"source_severity": "medium",
"confidence": 0.86,
"confidence_reasoning": "Lines 69-75 directly grant git mutation commands for --print mode, and lines 79-82 launch background agents. This is intentional workflow behavior, not a scanner artifact."
}
],
"low_findings": [],
"dangerous_patterns": [],
"files_scanned": 1,
"total_lines": 141,
"audit_model": "codex",
"audited_at": "2026-07-04T16:53:19.907Z",
"agent_auto_install_policy": "allowed",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Orchestrate Parallel Coding Agents",
"value_statement": "Large features are hard to split across autonomous coding agents. This skill provides a worktree-based workflow for issue design, wave planning, monitoring, merging, and cleanup.",
"seo_keywords": [
"Claude",
"Codex",
"Claude Code",
"parallel agents",
"git worktrees",
"AI coding agents",
"GitHub issues",
"agent orchestration",
"Claude CLI",
"parallel development"
],
"actual_capabilities": [
"Breaks large implementation work into isolated GitHub issues for separate agents.",
"Organizes issue batches into waves based on file overlap and dependencies.",
"Shows how to configure Claude permissions for non-interactive worktree commands.",
"Provides shell examples for launching, monitoring, merging, and cleaning worktrees.",
"Gives conflict handling guidance for sequential PR merges and rebases."
],
"limitations": [
"It does not create issues, branches, or worktrees by itself.",
"It assumes Claude CLI, Git, and GitHub CLI are installed and authenticated.",
"It requires manual review of diffs, PRs, and merge conflicts.",
"It can increase repository risk if broad git permissions are approved."
],
"use_cases": [
{
"title": "Plan a Feature Wave",
"description": "Split a feature into independent GitHub issues and run one agent per issue.",
"target_user": "Feature lead"
},
{
"title": "Batch Small Fixes",
"description": "Group small changes into waves while keeping same-file edits sequential.",
"target_user": "Repository maintainer"
},
{
"title": "Coordinate Integration Work",
"description": "Schedule dependent waves after agents finish implementation work and initial PRs land.",
"target_user": "Release engineer"
}
],
"prompt_templates": [
{
"title": "Plan a Safe First Wave",
"scenario": "Beginner planning",
"prompt": "Use orchestrating-parallel-agents to split this feature into three independent issues. Identify files, dependencies, and review steps before spawning agents."
},
{
"title": "Draft Agent-Ready Issues",
"scenario": "Issue preparation",
"prompt": "Draft issue bodies for a parallel agent wave. Include problem, solution, files to modify, implementation notes, and acceptance criteria."
},
{
"title": "Run and Monitor a Wave",
"scenario": "Operational execution",
"prompt": "Prepare the commands and checklist for launching agents for issues 101, 102, and 103. Include monitoring, logs, and failure handling."
},
{
"title": "Resolve Dependent Waves",
"scenario": "Advanced merge planning",
"prompt": "Design a multi-wave rollout for issues that share files. Show merge order, rebase checkpoints, and cleanup after PRs land."
}
],
"output_examples": [
{
"input": "A dashboard rewrite touches services, routes, and UI components.",
"output": "A wave plan separates independent service work, delays shared route edits, and lists review checkpoints before merge."
},
{
"input": "Two agents finished, and one failed before creating a PR.",
"output": [
"Inspect the failed agent log.",
"Complete the git steps manually in that worktree.",
"Create the PR after reviewing the diff."
]
},
{
"input": "Several PRs touch the same component file.",
"output": "A sequential merge order with rebase checkpoints after each landed PR."
}
],
"best_practices": [
"Keep each issue scoped to one to three files with clear acceptance criteria.",
"Review every diff and PR before merging or pushing.",
"Run same-file changes sequentially or assign them to one agent."
],
"anti_patterns": [
"Starting many agents against vague issues with no file guidance.",
"Pre-approving broad git permissions on a shared repository.",
"Merging parallel PRs without rebasing after earlier merges."
],
"faq": [
{
"question": "Does this skill run agents automatically?",
"answer": "No. It provides workflow guidance and command examples for launching agents with Claude CLI."
},
{
"question": "Can I use it with Codex?",
"answer": "Yes, as planning guidance. Replace Claude-specific command examples with equivalent Codex workflows when needed."
},
{
"question": "Does it require GitHub issues?",
"answer": "The workflow assumes issue numbers as prompts. You can adapt it to local task briefs."
},
{
"question": "Is non-interactive mode safe?",
"answer": "It needs caution. Keep permissions narrow and review changes before pushing or merging."
},
{
"question": "How many agents should I run?",
"answer": "Start with a small wave of independent tasks. Increase only after the review process works."
},
{
"question": "What should I do when conflicts happen?",
"answer": "Merge shared-file PRs sequentially. Rebase each remaining branch after earlier merges land."
}
]
},
"file_structure": [
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 141
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |