council-commission

council-commission is a command for Claude Code from SteveGJones/ai-first-sdlc-practices. It costs 34 tokens per session (2,271 once invoked), scanned A, original, MIT.

A project-onboarding command for a council of AI coding agents. It discovers available agents, studies the repository, tests the agents, and records a roster and policy.

In plain words
What is it for?
It helps commission a council, assess agent performance, record model diversity, and set operating rules.
Why use it?
It replaces ad-hoc model selection with project-specific evidence about which agents suit different tasks.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: positional $N argument; mentions Codex; mentions OpenCode.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the sdlc-model-council plugin — 1 skill, 7 commands, 2 agents shipped together

Good fit It helps commission a council, assess agent performance, record model diversity, and set operating rules.

Compare 6 commands from other repositories ↓
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 SteveGJones/ai-first-sdlc-practices
Claude Code
/plugin install sdlc-model-council

Made for: Claude Code.

Or install sdlc-model-council, the plugin that ships this one along with the rest of its 1 skill, 7 commands, 2 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.

agentmods badge for council-commission

README.md
[![agentmods](https://agentmods.dev/badge/commands/stevegjones/ai-first-sdlc-practices/council-commission/github.svg)](https://agentmods.dev/commands/stevegjones/ai-first-sdlc-practices/council-commission)
Your own site
<a href="https://agentmods.dev/commands/stevegjones/ai-first-sdlc-practices/council-commission"><img src="https://agentmods.dev/badge/commands/stevegjones/ai-first-sdlc-practices/council-commission/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.

agentmods 80×15 button for council-commission

Your own site · 80×15
<a href="https://agentmods.dev/commands/stevegjones/ai-first-sdlc-practices/council-commission"><img src="https://agentmods.dev/badge/commands/stevegjones/ai-first-sdlc-practices/council-commission.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,271 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00034 $0.02271
Opus 5 $0.00017 $0.01136
Sonnet 5 $0.00007 $0.00454
Haiku 4.5 $0.00003 $0.00227

Measured 10d ago against content hash 45b37d7bdd25, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-13, from the pricing page.

Security

Grade A, and why

council-commission 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 10d 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/sdlc-model-council/commands/council-commission.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commission this project for sdlc-model-council: discover which models are actually reachable, characterize what the repo needs, audition them at a chosen depth, and write .sdlc/model-council/{roster.json,roster.md, diversity.json,policy.json,commission.json}. Load the council-policy skill now — every routing/play/posture decision below leans on it.

Arguments: $ARGUMENTS — optional audition=skip|calibrate|standard|full. If omitted, this is a real decision with real cost implications (see step 3) — ask the user rather than guessing.

Do this:

0. Pre-flight re-commission check

If .sdlc/model-council/commission.json already exists, this project has been commissioned before. Read it, show the prior ts and audition level, and confirm with the user before continuing — re-commissioning overwrites roster.json, roster.md, diversity.json, and policy.json in place. If they only want a refresh (same fleet, new evidence), point at /sdlc-model-council:council-assess or /sdlc-model-council:council-roster rebuild instead, which don't touch policy.

1. Discover — token-free

${CLAUDE_PLUGIN_ROOT}/scripts/extdel.sh list-backends --json

gives you which backends (codex, agy, opencode, …) are registered, installed, and authenticated. For every backend reported installed: yes / authenticated, list its actual model ids directly against the CLI (still token-free — a model listing, not a turn): agy models for agy, opencode models for opencode (codex is addressed as codex:default@<effort>, no separate model-listing call). Build the full set of reachable adapter:model[@effort] addresses.

For each address, resolve its pricing family and free flag:

${CLAUDE_PLUGIN_ROOT}/scripts/council/priors.py resolve <address> \
  --priors-dir ${CLAUDE_PLUGIN_ROOT}/scripts/council/priors

then look up that family in ${CLAUDE_PLUGIN_ROOT}/scripts/council/pricing.json (.families.<family>.free). Present the discovered fleet as a table: address, family, free y/n. This is the fleet snapshot that goes into commission.json at the end — capture it now.

Read the full file on GitHub · 175 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.

  1. 10d ago First seen · 175 lines · 34 tokens per session scan A 45b37d7bdd25

Subscribe to this mod's changes

council-commission is a command published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 2,271 once invoked, about $0.0002 per session on Opus 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 2026-09-03.