A configuration command for choosing which external AI consultants and local subagents a Council review can use. It also checks installed command-line tools and sets review backends, models, and time limits.

It detects tools, shows current status, enables or disables Gemini, Codex, GLM, and Kimi consultants, selects a quick consultant, configures subagent backends and models, and sets timeouts.

It avoids manually editing settings when available subscriptions, installed tools, or preferred review services change. It makes the enabled consultants and review setup visible.

config — Command for Claude Code by rube-de/cc-skills

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add rube-de/cc-skills

Claude Code

/plugin install council

Made for: Claude Code.

Or install council, the plugin that ships this one along with the rest of its 3 skills, 1 command, 7 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/rube-de/cc-skills/config/github.svg)](https://agentmods.dev/commands/rube-de/cc-skills/config)

Your own site

<a href="https://agentmods.dev/commands/rube-de/cc-skills/config"><img src="https://agentmods.dev/badge/commands/rube-de/cc-skills/config/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/rube-de/cc-skills/config"><img src="https://agentmods.dev/badge/commands/rube-de/cc-skills/config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,035 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00023	$0.02035
Opus 5.5	$0.00009	$0.00814
Sonnet 5.5	$0.00005	$0.00407
Haiku 4.5	$0.00002	$0.00203

Measured 23d ago against content hash 8de1f154d7b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

config scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 23d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/council/commands/config.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/council:config — Council Consultant Configuration

Configure which external AI consultants are enabled for Council reviews and consultations based on your active subscriptions and installed CLIs.

Usage

/council:config                            # Interactive setup & detection wizard
/council:config show                       # Display current configuration & CLI status
/council:config enable <consultant>        # Enable a consultant (gemini, codex, glm, kimi)
/council:config disable <consultant>       # Disable a consultant
/council:config quick <consultant|auto>    # Set preferred quick mode external consultant
/council:config subagent backend <type>    # Set Claude subagent backend (native, omp, claude-cli)
/council:config subagent model <model>     # Set deep review model (opus, sonnet)
/council:config subagent enable <name>     # Enable subagent (claude-deep-review, claude-codebase-context, review-scorer)
/council:config subagent disable <name>    # Disable subagent
/council:config timeout <seconds>          # Set per-consultant timeout in seconds
/council:config detect                     # Probe installed CLIs & active subscriptions
/council:config init [--auto] [--force]    # Initialize configuration (.dev/council/config.json)

Add --global to any command to target ~/.config/council/config.json instead of the project-local .dev/council/config.json.

Configuration Precedence

Project-local: .dev/council/config.json (takes precedence; should be added to .gitignore)
User-global: ~/.config/council/config.json (fallback across all projects)
Default: Gemini & Codex enabled, GLM & Kimi disabled

Workflow

1. Parse Arguments

Resolve the config utility path:

if [ -n "$CLAUDE_PLUGIN_ROOT" ] && [ -f "$CLAUDE_PLUGIN_ROOT/scripts/council-config.sh" ]; then
  CONFIG_SCRIPT="$CLAUDE_PLUGIN_ROOT/scripts/council-config.sh"
elif [ -f "plugins/council/scripts/council-config.sh" ]; then
  CONFIG_SCRIPT="plugins/council/scripts/council-config.sh"
elif [ -n "$(git rev-parse --show-toplevel 2>/dev/null)" ] && [ -f "$(git rev-parse --show-toplevel)/plugins/council/scripts/council-config.sh" ]; then
  CONFIG_SCRIPT="$(git rev-parse --show-toplevel)/plugins/council/scripts/council-config.sh"
else
  echo "Error: council-config.sh not found. Ensure CLAUDE_PLUGIN_ROOT is set or run within the cc-skills repository." >&2
  exit 1
fi

Check if $ARGUMENTS contains the standalone flag token --global (not as part of another argument like --globalfoo). If present, pass --global as an explicit, separate flag argument to script commands (e.g. show --global).

Read the full file on GitHub · 189 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

23d ago First seen · 189 lines · 23 tokens per session scan A 8de1f154d7b2

Subscribe to this mod's changes

config is a command published in the GitHub repository rube-de/cc-skills (10 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 2,035 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-27.

Building agents Claude Code Code review Multi-Agent agent-teams ai-council claude-code-plugin

config

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/council:config — Council Consultant Configuration

Usage

Configuration Precedence

Workflow

1. Parse Arguments

What this file has done since we first saw it

Other commands, from other repositories

poc

rfc

release

exception

phase-review

review-pr