dispatching-parallel-agents

An agent skill by obra, from obra/superpowers. Tags: api, developer-tools, mcp.

What it does

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add obra/superpowers --skill dispatching-parallel-agents

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/obra/superpowers
cp -r superpowers/skills/dispatching-parallel-agents ~/.claude/skills/dispatching-parallel-agents

Safety box score

Grade A, minimal risk: 4 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is a coordination guide for splitting independent debugging work across multiple agents. It does not ship executable code or touch local files, but it does encourage concurrent agent work, which can create edit conflicts if the tasks are not truly independent.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	The skill is only a markdown guide; it contains no scripts, shell commands, or code execution paths.
Network access	0 (none)	No downloading, API calls, or remote data transfer is described.
Filesystem reach	0 (none)	It does not read, write, or delete files; it only discusses how to assign tasks.
Secrets & credentials	0 (none)	There is no mention of tokens, keys, passwords, or credential stores.
Privilege & persistence	0 (none)	It does not request sudo, installs, services, or OS/shell configuration changes.
Instruction hijack surface	0 (none)	The text does not tell the agent to ignore instructions, hide behavior, or follow fetched external content.
Irreversible actions	1 (low)	It explicitly recommends parallel agent dispatch — e.g. "Issue all three subagent dispatches in the same response" — but only for bounded debugging work.
Transparency	0 (none)	The skill is fully readable markdown with no binaries, blobs, or decoded-at-runtime content.

Before installing

Read `SKILL.md` to confirm it only provides coordination guidance and no executable payloads.
Use it only for tasks that do not share files or state; concurrent edits can conflict.
If you plan to use it on a real repo, verify your agent runner can isolate per-agent workspaces or branches.

Rated 2026-10-20 by an automated review of 1 file from the skill's repository.

Source

Repository: obra/superpowers (all skills from this repository)
Path: skills/dispatching-parallel-agents/SKILL.md
Branch: main
Updated: 2026-09-19

diagnosing-superpowers — Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results.
subagent-driven-development — Use when executing implementation plans with independent tasks in the current session
atlassian-mcp — Integrates with Atlassian products to manage project tracking and documentation via MCP protocol.
claude-api — Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.
figma — Import Figma content into a HyperFrames composition — rendered assets, brand tokens, components.
hyperframes-registry — Search, install, and wire registry blocks and components into HyperFrames compositions.