agents: Skill for Claude Code

.agents/skills/workflow-parallel-agents/SKILL.md

dispatching-parallel-agents is a skill for Claude Code, Codex from mtnyilmaz/agents. It costs 44 tokens per session (1,949 once invoked), scanned A, original, MIT.

A method for sending separate, unrelated coding investigations to different agents at the same time. The problems must not depend on shared files or on each other's results.

In plain words
What is it for?
Use it to investigate unrelated test failures, subsystems, security checks, or dependency updates concurrently, then combine the results.
Why use it?
It reduces waiting when several independent bugs, failing tests, audits, or documentation tasks need attention.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions Claude Code; installed under .agents/ (shared by several agents).

This is mtnyilmaz/agents's own configuration. It tells Claude Code and Codex how to work on agents itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agents configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mtnyilmaz/agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mtnyilmaz/agents/main/.agents/skills/workflow-parallel-agents/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mtnyilmaz/agents

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for dispatching-parallel-agents

README.md
[![agentmods](https://agentmods.dev/badge/skills/mtnyilmaz/agents/workflow-parallel-agents/github.svg)](https://agentmods.dev/skills/mtnyilmaz/agents/workflow-parallel-agents)
Your own site
<a href="https://agentmods.dev/skills/mtnyilmaz/agents/workflow-parallel-agents"><img src="https://agentmods.dev/badge/skills/mtnyilmaz/agents/workflow-parallel-agents/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for dispatching-parallel-agents

Your own site · 80×15
<a href="https://agentmods.dev/skills/mtnyilmaz/agents/workflow-parallel-agents"><img src="https://agentmods.dev/badge/skills/mtnyilmaz/agents/workflow-parallel-agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,949 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00044 $0.01949
Opus 5.5 $0.00018 $0.00780
Sonnet 5.5 $0.00009 $0.00390
Haiku 4.5 $0.00004 $0.00195

Measured 1mo ago against content hash 76222cf516dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dispatching-parallel-agents 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 1mo 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.

.agents/skills/workflow-parallel-agents/SKILL.md · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dispatching Parallel Agents

Overview

When you have multiple independent problems — different failing test files, different broken subsystems, different bugs — investigating them sequentially wastes wall-clock time. Each investigation is independent, so each can happen concurrently in its own subagent.

Core principle: One subagent per independent problem domain. Let them work in parallel. Integrate at the end.

Distinct from workflow-subagent-driven: That skill executes a plan serially (one task at a time) because plan tasks typically share files. This skill runs investigations concurrently because the problems are disjoint.

When to Use

  • 3+ test files failing with clearly unrelated root causes
  • Multiple subsystems broken independently (e.g. auth + billing + email)
  • Independent code audits (e.g. run all SAST skills at once)
  • Parallel documentation / dependency upgrades across unrelated modules
  • Each problem can be understood and fixed without state from the others

When NOT to use:

  • Failures look related — fixing one might fix the others (investigate together first)
  • You need full-system context to understand what's broken
  • Exploratory debugging — you don't yet know what the problem is
  • Subagents would touch the same files (they will conflict)
                  ┌─ Multiple problems?
                  │        │
                  │        ▼
                  │   Independent? ──── no ── Single investigation, sequential
                  │        │
                  │        yes
                  │        │
                  │        ▼
                  │   Shared files?  ──── yes ── Sequential subagents (avoid conflicts)
                  │        │
                  │        no
                  │        │
                  │        ▼
                  └──→ PARALLEL DISPATCH

The Workflow

1. Identify independent domains
2. Build one focused prompt per domain
3. Dispatch all subagents in the same message (parallel)
4. Collect returns
5. Verify no file-level conflicts
6. Run the full suite
7. Integrate

Read the full file on GitHub · 221 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 1mo ago First seen · 221 lines · 44 tokens per session scan A 76222cf516dc

Subscribe to this mod's changes

dispatching-parallel-agents is a skill published in the GitHub repository mtnyilmaz/agents (6 stars, last pushed 5mo ago), licensed MIT. It adds 44 tokens to every session and 1,949 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.

Related

Other skills, from other repositories

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

component-fixtures

Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.

microsoft/vscode · 53 tokens