Skip to content
Agentmart
Submit a tool

multi-agent-deliberation

Use for high-stakes decisions: architecture forks, build-vs-buy, competitive response, major refactors, or when the user wants multi-agent debate.

Skill by AVIDS2

IndexedMIT★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/avids2-multi-agent-deliberation

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use for high-stakes decisions: architecture forks, build-vs-buy, competitive response, major refactors, or when the user wants multi-agent debate. Spawns diverse perspectives (or Codex second opinion) and synthesizes a recommendation. Do NOT use for trivial choices or every small implementation detail.

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/multi-agent-deliberation

What's inside

Skill name
multi-agent-deliberation
Description
Use for high-stakes decisions: architecture forks, build-vs-buy, competitive response, major refactors, or when the user wants multi-agent debate. Spawns diverse perspectives (or Codex second opinion) and synthesizes a recommendation. Do NOT use for trivial choices or every small implementation detail.
License
MIT
Instructions
73 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Multi-Agent Deliberation

When a wrong call is expensive, prefer competing lenses — then decide. **Optional**: skip for clear choices or when the user wants speed.

## When to Use

- Build vs buy / build vs wrap competitor
- LangGraph vs Pi vs custom orchestration (after `agent-framework-choice` still unclear)
- "Should we pivot given competitor X?"
- Large rewrite vs incremental
- User explicitly asks for multi-agent or second opinion

## Procedure

### 1. Frame the decision

Write:

- Question (one sentence)
- Constraints (time, skills, stack, distribution)
- Success metric
- Deadline / reversibility (one-way door?)

### 2. Run 2–3 lenses (parallel when possible)

Pick lenses that disagree productively:

| Lens | Focus |
|------|--------|
| **User/value** | Does this help the buyer this month? |
| **Risk/security** | What fails in prod? |
| **Tech debt / YAGNI** | Simplest path (ponytail spirit) |
| **Competitive** | How does this position vs named alternatives? |
| **Codex/rescue** | Independent second implementation or review |

Implementation options:

- Claude Code `Agent` tool with distinct system prompts per lens
- Codex plugin `/rescue` or `/adversarial-review` when available
- Sequential self-roles only if subagents unavailable (label each role clearly)

### 3. Synthesize (you, main agent)

Produce:

```markdown
## Decision question
## Options
## Lens votes (table)
## Recommendation
## Dissent / residual risks
## What would change the decision
## Proposed next experiment (smallest test)
```

Do **not** average into mush. Pick a recommendation. Surface dissent.

### 4. User owns the call

Present synthesis; user confirms. Record in `docs/decisions/` or dev-log when multi-session.

## Anti-Patterns

- Five agents agreeing with the same prompt (fake diversity)
- Deliberating UI padding color
- Hiding the recommendation behind "it depends" with no default
- Skipping research gates by debating vibes only — attach evidence

## Related

- `product-bootstrap`, `research-before-build`, `agent-framework-choice`

From AVIDS2/avid-skill, MIT.

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Jul 23, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from AVIDS2

Cite this page

multi-agent-deliberation skill. Agent Mart. https://agentmart.dev/skills/avids2-multi-agent-deliberation (last updated 2026-10-24)