parallel-execution

Instructions for running independent coding tasks at the same time when they do not share files or depend on one another.

In plain words
What is it for?
Finding independent subtasks, grouping them into execution batches, and assigning each batch to separate coding agents.
Why use it?
Parallel work can reduce the time needed for multi-part changes while keeping dependent tasks in the correct order.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/darrenhinde/openagentscontrol/parallel-execution
Any agent
npx skills add darrenhinde/OpenAgentsControl --skill parallel-execution
Clone the repo
git clone --depth 1 https://github.com/darrenhinde/OpenAgentsControl

Made for: Claude Code, Codex.

Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,099 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00021 $0.01099
Opus 5 $0.00010 $0.00549
Sonnet 5 $0.00004 $0.00220
Haiku 4.5 $0.00002 $0.00110

Measured 2d ago against content hash b902b923e646, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

parallel-execution scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/claude-code/skills/parallel-execution/SKILL.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Parallel Execution

Overview

Execute multiple independent tasks simultaneously using multiple subagent invocations in a single message. Reduces implementation time by 50-80% for multi-component features.

Announce at start: "I'm using parallel-execution to run [N] independent tasks simultaneously."

The Process

Step 1: Identify Parallel Tasks

Check subtask JSON files for parallel: true:

bash .opencode/skills/task-management/router.sh parallel {feature}

Output shows which tasks can run together:

Batch 1 (Ready now):
- subtask_01.json (parallel: true)
- subtask_02.json (parallel: true)

Batch 2 (After Batch 1):
- subtask_03.json (depends_on: ["01", "02"])

Step 2: Execute Parallel Batch

Make multiple task() calls in SINGLE message:

I'll execute Batch 1 tasks in parallel:

task(
  subagent_type="CoderAgent",
  description="Execute subtask 01",
  prompt="Read .tmp/tasks/feature/subtask_01.json and implement..."
)

task(
  subagent_type="CoderAgent",
  description="Execute subtask 02",
  prompt="Read .tmp/tasks/feature/subtask_02.json and implement..."
)

CRITICAL: Both task() calls in SAME message—not separate messages.

Step 3: Wait for All to Complete

All tasks in batch must complete before proceeding to next batch.

Step 4: Verify Batch Completion

bash .opencode/skills/task-management/router.sh status {feature}

Check all tasks in batch marked status: "completed".

Step 5: Execute Next Batch

Once Batch 1 complete, proceed to Batch 2:

task(
  subagent_type="CoderAgent",
  description="Execute subtask 03",
  prompt="Read .tmp/tasks/feature/subtask_03.json and integrate..."
)

Example: Converting Multiple Files

I'll convert these 5 subagent files in parallel:

task(subagent_type="CoderAgent", description="Convert auth-agent",
     prompt="Convert .opencode/agent/subagents/auth-agent.md to new format...")

task(subagent_type="CoderAgent", description="Convert user-agent",
     prompt="Convert .opencode/agent/subagents/user-agent.md to new format...")

task(subagent_type="CoderAgent", description="Convert payment-agent",
     prompt="Convert .opencode/agent/subagents/payment-agent.md to new format...")

task(subagent_type="CoderAgent", description="Convert notification-agent",
     prompt="Convert .opencode/agent/subagents/notification-agent.md to new format...")

task(subagent_type="CoderAgent", description="Convert analytics-agent",
     prompt="Convert .opencode/agent/subagents/analytics-agent.md to new format...")

Read the full file on GitHub · 169 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 169 lines · 21 tokens per session scan A b902b923e646

Subscribe to this mod's changes

parallel-execution is a skill published in the GitHub repository darrenhinde/OpenAgentsControl (4,815 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 1,099 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

azure-openai-to-responses

Migrate Python apps from Azure OpenAI Chat Completions to the Responses API. Covers AzureOpenAI/AsyncAzureOpenAI client migration to the v1 endpoint, streaming, tools, structured output, multi-turn, EntraID auth, and model compatibility checks. Python-focused, Azure OpenAI-specific. USE FOR: migrate to responses API…

microsoft/ai-agents-for-beginners · 185 tokens

knowledge-base

Create and maintain a Markdown knowledge base that any AI agent can read, search, and update. Use when the user wants to start a knowledge base, add or update notes, organize docs/notes for an agent or LLM to consume, build an index of notes, or run a cleanup/maintenance pass on an existing MD knowledge base. Triggers…

wonderwhy-er/DesktopCommanderMCP · 112 tokens

peer-review

Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writing, manuscript revision. For evaluating…

xintaofei/codeg · 71 tokens

statistical-power

Sample-size and statistical power calculations for planning studies. Use whenever someone asks "how many subjects/samples/replicates do I need", wants an a priori power analysis, a minimum detectable effect (MDE), a power curve, or needs to justify a sample size for a grant, IRB protocol, or pre-registration. Covers…

xintaofei/codeg · 190 tokens

build-teaql-app

Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…

teaql/teaql-agent-kit · 112 tokens

dd-code-generation

Use pup CLI for immediate Datadog operations or generate code for integration into applications.

DataDog/pup · 16 tokens