Is the Agents Consilium skill free?

Yes. The skill itself is free from CodeAlive-AI/ai-driven-development. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Agents Consilium SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.

How do I install Agents Consilium?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Agents Consilium with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Agents Consilium

Runs Codex/OpenCode/Gemini/Claude in parallel for independent second opinions and 2-specialist code review.

by CodeAlive-AI · CodeAlive-AI/ai-driven-development

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 13, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 51112ea

⚠ The author changed this skill after we tested it. The verdict below describes the version we ran on Jul 13, 2026; it's queued for a re-test.

Re-ran the live dry runs against the new upstream: --list-agents printed the grounded environment check (Codex and OpenCode backends unavailable here, Claude Code available), now correctly listing the freshly added Grok 4.5 and Claude Fable profiles, and superreview --dry-run validated its full multi-stage plan and exited 0. The verbatim git clone plus cp install still works from a bare HOME with no ~/.claude. Nothing structural moved since our first pass. The upstream edits are additive config and doc polish, not behaviour changes, so the grounded-check advantage that earned the pass is intact.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 4/5

What Agents Consilium does

Dispatches the same prompt to multiple external AI CLIs (Codex, Gemini, OpenCode, headless Claude Code) in parallel for architecture decisions, code review, and bug investigation, then leaves synthesis of the independent opinions to the caller instead of running a homogenized debate. Ships a focused security+correctness code-review mode plus multi-stage superreview/ultrareview pipelines with an LLM judge for high-stakes diffs touching money, auth, or persistence. Triggers on requests for a second opinion, multi-model code review, or consensus on an ambiguous or high-stakes technical decision -- explicitly not for questions answerable from docs or a quick repo search.

How to install Agents Consilium

git clone https://github.com/CodeAlive-AI/ai-driven-development
cd ai-driven-development
mkdir -p ~/.claude/skills
cp -r skills/agents-consilium ~/.claude/skills/agents-consilium

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Agents Consilium

/agents-consilium Runs Codex/OpenCode/Gemini/Claude in parallel for independent second opinions and 2-specialist code review.

It also activates on plain-language prompts like these:

Get a second opinion from Codex and Gemini on this
Run a multi-model code review on my auth changes
Ask several AI CLIs to review this risky diff

Frequently asked questions

Is the Agents Consilium skill free?: Yes. The skill itself is free from CodeAlive-AI/ai-driven-development. SkillProof publishes the install command and an independent test verdict at no cost.
Does Agents Consilium work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 13, 2026. Verdict: Tested · Works. Re-ran the live dry runs against the new upstream: --list-agents printed the grounded environment check (Codex and OpenCode backends unavailable here, Claude Code available), now correctly listing the freshly added Grok 4.5 and Claude Fable profiles, and superreview --dry-run validated its full multi-stage plan and exited 0. The verbatim git clone plus cp install still works from a bare HOME with no ~/.claude. Nothing structural moved since our first pass. The upstream edits are additive config and doc polish, not behaviour changes, so the grounded-check advantage that earned the pass is intact.
What is the Agents Consilium SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Agents Consilium?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Agents Consilium with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.