Committee of two: contrasting agents for root-cause analysis and planning
Spawn two high-reasoning agents from contrasting profiles in parallel to break out of loops and converge on a plan
- What
- Spawn two high-reasoning agents from contrasting profiles in parallel to break out of loops and converge on a plan
- Cost
- Free
- Needs
- a Paseo-configured environment (the paseo skill and configured agent profiles) — this skill does not work standalone
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Selected by Skill Harbor — short listing (the repo states no license, so no content is reproduced): @getpaseo's committee skill — when stuck, looping, tunnel-visioning, or facing a hard planning problem, form a committee of two high-reasoning agents from contrasting profiles (preferably different provider families, selected after reading the configured profiles and their notes via list_profiles), give them the same problem-level prompt in parallel, then resolve their disagreements by passing arguments between them until they converge — and report where they diverged and how they resolved it. Hard rules: analysis only (every committee prompt ends with a no-edits suffix — no file edits, no code); trust the finish notification, don't poll or hurry up (models can reason 15–30 minutes). Honest caveats: not standalone — only works inside a Paseo-configured environment (the paseo skill must be read first, and Paseo's provider discovery covers missing profiles); license not stated by the source repo — short listing with a link only, nothing copied. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Committee of two is a free Muse skill that spawns two high-reasoning agents from contrasting profiles in parallel to break out of loops and converge on a plan. When you are stuck or facing a hard planning problem, both agents get the same prompt, then disagreements are resolved by passing arguments between them until they converge.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox and failed · Nov 18, 2026 · Installation failed📌 Pinned version: commit 718ed93Step 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: a Paseo-configured environment (the paseo skill and configured agent profiles) — this skill does not work standalone Install "Committee of two: contrasting agents for root-cause analysis and planning" for me. It gives my agent @getpaseo's committee workflow: read the paseo skill and configured profiles, pick two contrasting high-reasoning agents, spawn them in parallel with the same problem-level prompt (analysis only — no-edits suffix), resolve disagreements between them until they converge, and report where they diverged. IMPORTANT: the repo states no license — fetch from the link only, and reproduce nothing beyond the link. Repository: https://raw.githubusercontent.com/getpaseo/paseo/718ed932b7843cde0b156ff30ec6adf42e828a18/skills/paseo-committee/SKILL.md Pinned version: install the code at commit 718ed932b7843cde0b156ff30ec6adf42e828a18 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 (and any helper files) from the repository path 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. 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 "paseo-committee". 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. read the paseo skill and configure at least two contrasting agent profiles first — the committee only runs on top of Paseo). 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. 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
- 718ed93 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox and failed · Nov 18, 2026 — Installation failed · Observed during the install test: registry.npmjs.org
- 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.