Dispatching Parallel Agents
One agent per independent problem domain: craft self-contained prompts, work concurrently
- What
- One agent per independent problem domain: craft self-contained prompts, work concurrently
- Cost
- Free
- Needs
- an AI agent harness that supports subagents (Claude Code, Codex, Pi, Antigravity, Hermes, or Muse)
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — one of the original superpowers meta-skills by @obra (the upstream behind the much-forked framework; distinct from the magentosh/bankai-skills forks already in this catalog and from the obra fiches published at lot 33, using-superpowers and executing-plans). When multiple unrelated failures hit (different test files, different subsystems, different bugs), investigating sequentially wastes time — dispatch one agent per independent problem domain and let them work concurrently. Teaches when to use it (3+ failing test files with different root causes, multiple subsystems broken independently, no shared state) and when not to (related failures — fixing one might fix others — or full system state needed), plus the craft: build targeted self-contained prompts so agents never inherit your session's context or history, and avoid the classic mistakes (too broad, no context, no constraints). The explicit counterpart of executing-plans (lot 33), which teaches inline execution WITHOUT subagents — that fiche even says to prefer subagent-driven development in some cases; this skill is that subagent-driven development. By @obra, listed here with credit to its creator. Skill Harbor never reviews the code, review it yourself before use.
Version:
Quick answer
Dispatching Parallel Agents is a free Muse skill that teaches your Muse to dispatch one agent per independent problem domain and let them work concurrently, instead of investigating unrelated failures sequentially. It covers when to use parallel agents, when not to, and how to craft self-contained prompts so agents never inherit your session context.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit bb92a77Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: an AI agent harness that supports subagents (Claude Code, Codex, Pi, Antigravity, Hermes, or Muse) Install "Dispatching Parallel Agents" for me. One agent per independent problem domain: craft self-contained prompts, work concurrently Repository: https://raw.githubusercontent.com/obra/superpowers/bb92a77741419a4ab5f06e711a283343f1ada0c3/skills/dispatching-parallel-agents/SKILL.md Pinned version: install the code at commit bb92a77741419a4ab5f06e711a283343f1ada0c3 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file for the obra-dispatching-parallel-agents skill from the repository into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "obra-dispatching-parallel-agents". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. any accounts, API keys, or CLI tools mentioned in the prerequisites above). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. Never ask me to paste secrets in chat — credentials go through the secure vault or environment variables. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- bb92a77 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.