deliberation SKILL.md skillC

This file is byte-identical to the first copy the registry indexed, one of 3 indexed copies. Same content hash, so the same checks give both the same grade.

deliberation from antonbabenko/deliberation is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add antonbabenko/deliberation/deliberation@git:20261015.e8f55c9

Pins git:20261015.e8f55c9 in mdr.lock. Pin the fingerprint instead.

Audit grade
C, 15 of 17 checks passed
Kind
SKILL.md skill
Repository
antonbabenko/deliberation
Path
.agents/skills/deliberation/SKILL.md
Versions recorded
10
Latest version
git:20261015.e8f55c9, committed Oct 15, 2026
First version recorded
Oct 5, 2026
Size
16,099 bytes
Repository stars
177
License
MIT

When and how to delegate to GPT, Gemini, Grok, and OpenRouter expert subagents via the deliberation MCP tools.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

<!-- GENERATED by scripts/sync-hosts.js - edit the source under prompts/, docs/tool-guide.md, or examples/, then regenerate. -->

# Deliberation

Host-neutral guidance for any AI coding agent connected to the deliberation MCP
server (Claude Code, Cursor, Codex, Kiro, Antigravity, Windsurf, Zed, and
others): what the tools do and when to delegate. The per-host skills and Powers
are generated from this file by `scripts/sync-hosts.js`.

## What deliberation is

A single MCP server that exposes GPT (via the Codex CLI), Gemini 3 (via the
Antigravity CLI), Grok (via the xAI API), local models (Ollama, LM Studio), and
OpenRouter models (400+, advisory) as expert subagents. You stay the primary
agent. When a task benefits from a second opinion or cross-model review, call
one of the tools below, read the result, and apply your own judgment. Every tool
here is ADVISORY: this server reads and reasons, it never edits your files.
(Implementation exists only in the Claude Code plugin's standalone Gemini
bridge, which this server does not expose.)

## Tools

Fan-out and single-provider:

- `ask-all` - send one question to GPT, Gemini, Grok, local models, and
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add antonbabenko/deliberation/deliberation@sha256:4e4ae432a11136d3

The line at the top of this page pins the label git:20261015.e8f55c9, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_txufhai5tti365c7.svg)](https://markdownregistry.com/a/art_txufhai5tti365c7)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 10 versions of this file, between Oct 5, 2026 and Oct 15, 2026, about one every day.

versioncommittedcommitsizeaudit
git:20261015.e8f55c9 latest2026-10-15 e8f55c9 16,099 BC view · diff
git:20261011.e7768682026-10-11 e776868 16,049 BC view · diff
git:20261010.050a6a72026-10-10 050a6a7 15,738 BC view · diff
git:20261008.f19442d2026-10-08 f19442d 15,658 BC view · diff
git:20261008.29a04432026-10-08 29a0443 15,588 BC view · diff
git:20261008.893bd582026-10-08 893bd58 15,457 BC view · diff
git:20261008.b0644d62026-10-08 b0644d6 15,503 BC view · diff
git:20261007.915c4582026-10-07 915c458 15,315 BC view · diff
git:20261006.9138f412026-10-06 9138f41 13,491 BC view · diff
git:20261005.df100b72026-10-05 df100b7 13,203 BC view

Audit of the latest version

C  15 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No recursive delete of root, home or parent (matched: rm -rf ~/)
  • fail: No link to a raw IP address (matched: http://127.0.0.1)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (16099 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

antonbabenko/deliberation · 177 stars · license MIT · pushed 2026-10-15 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_txufhai5tti365c7
GET https://markdownregistry.com/api/v1/resolve?ref=antonbabenko/deliberation/deliberation
GET https://markdownregistry.com/api/v1/blob/4e4ae432a11136d30dd9e487446091001bdf19c8539020aa9a87035e9bb796a4

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from antonbabenko/deliberation

architect SKILL.md skill
antonbabenko/deliberation · .agents/skills/architect/SKILL.md · System design, tradeoffs, and complex technical decisions.
git:20261008.893bd58 · audit A · 177 stars
code-reviewer SKILL.md skill
antonbabenko/deliberation · .agents/skills/code-reviewer/SKILL.md · Find bugs, security holes, and maintainability issues in a diff or file.
git:20261008.893bd58 · audit A · 177 stars
debugger SKILL.md skill
antonbabenko/deliberation · .agents/skills/debugger/SKILL.md · Rank root-cause hypotheses and propose the smallest safe fix.
git:20261008.893bd58 · audit A · 177 stars
plan-reviewer SKILL.md skill
antonbabenko/deliberation · .agents/skills/plan-reviewer/SKILL.md · Validate that a work plan is executable before work starts.
git:20261008.893bd58 · audit A · 177 stars
reload-mcp SKILL.md skill
antonbabenko/deliberation · .agents/skills/reload-mcp/SKILL.md · Gracefully cycle dashboard and audit MCP processes after deliberation is updated.
git:20261008.893bd58 · audit A · 177 stars
researcher SKILL.md skill
antonbabenko/deliberation · .agents/skills/researcher/SKILL.md · Research external libraries, APIs, and best practices, with evidence.
git:20261008.893bd58 · audit A · 177 stars
scope-analyst SKILL.md skill
antonbabenko/deliberation · .agents/skills/scope-analyst/SKILL.md · Catch ambiguities and hidden requirements before planning.
git:20261008.893bd58 · audit A · 177 stars
security-analyst SKILL.md skill
antonbabenko/deliberation · .agents/skills/security-analyst/SKILL.md · Threat-model and find vulnerabilities, with practical remediation.
git:20261008.893bd58 · audit A · 177 stars
deliberation Cursor rule
antonbabenko/deliberation · .cursor/rules/deliberation.mdc · Use deliberation MCP experts for review and second opinions
git:20260601.52dd6fe · audit A · 177 stars
architect SKILL.md skill
antonbabenko/deliberation · .gemini/skills/architect/SKILL.md · System design, tradeoffs, and complex technical decisions.
git:20261008.893bd58 · audit A · 177 stars
code-reviewer SKILL.md skill
antonbabenko/deliberation · .gemini/skills/code-reviewer/SKILL.md · Find bugs, security holes, and maintainability issues in a diff or file.
git:20261008.893bd58 · audit A · 177 stars
debugger SKILL.md skill
antonbabenko/deliberation · .gemini/skills/debugger/SKILL.md · Rank root-cause hypotheses and propose the smallest safe fix.
git:20261008.893bd58 · audit A · 177 stars

Every file in antonbabenko/deliberation

Other files named deliberation

deliberation SKILL.md skill
antonbabenko/deliberation · plugins/deliberation/skills/deliberation/SKILL.md · When and how to delegate to GPT, Gemini, Grok, and OpenRouter expert subagents via the deliberation MCP tools.
git:20261015.e8f55c9 · audit C · 177 stars
deliberation Cursor rule
antonbabenko/deliberation · .cursor/rules/deliberation.mdc · Use deliberation MCP experts for review and second opinions
git:20260601.52dd6fe · audit A · 177 stars
deliberation SKILL.md skill
antonbabenko/deliberation · .gemini/skills/deliberation/SKILL.md · When and how to delegate to GPT, Gemini, Grok, and OpenRouter expert subagents via the deliberation MCP tools.
git:20261015.e8f55c9 · audit C · 177 stars
deliberation SKILL.md skill
chrono-meta/forge-harness · plugins/fh-commons/skills/deliberation/SKILL.md · Multi-perspective synthesis structure — Innovator (propose) → Devil-Advocate (challenge) → Mediator (synthesize)…
git:20260811.eede7ad · audit A · 30 stars
deliberation SKILL.md skill
2389-research/deliberation · skills/deliberation/SKILL.md · Structured deliberation support for decisions worth sitting with — ethical questions, architecture choices, trade-offs…
git:20260925.cc47dcd · audit A · 9 stars
deliberation SKILL.md skill
brunob54/superpowers-orchestrator · skills/deliberation/SKILL.md · Use BEFORE brainstorming when facing a complex architectural, technology, or design decision where the options are not…
git:20260415.0a78a70 · audit A · 3 stars

Browse by kind, by grade C, or by owner.