What is council-roster?

A command that displays a project's council roster: its available AI agents, roles, performance grades, costs, response times, and how differently they tend to perform.

It helps review model assignments, compare agent pairs, and identify complementary agents for future council tasks.

It lets you inspect the current agent choices without starting a new assessment or spending tokens.

council-roster — Command for Claude Code by SteveGJones

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/stevegjones/ai-first-sdlc-practices/council-roster/github.svg)](https://agentmods.dev/commands/stevegjones/ai-first-sdlc-practices/council-roster)

Your own site

<a href="https://agentmods.dev/commands/stevegjones/ai-first-sdlc-practices/council-roster"><img src="https://agentmods.dev/badge/commands/stevegjones/ai-first-sdlc-practices/council-roster/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/stevegjones/ai-first-sdlc-practices/council-roster"><img src="https://agentmods.dev/badge/commands/stevegjones/ai-first-sdlc-practices/council-roster.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 910 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	$0.00028	$0.00910
Opus 5	$0.00014	$0.00455
Sonnet 5	$0.00006	$0.00182
Haiku 4.5	$0.00003	$0.00091

Measured 10d ago against content hash fb62708e94aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-13, from the pricing page.

Security

Grade A, and why

council-roster 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-roster.md · 66 lines

What it actually says

Show the project's current model-council roster. This is a read of .sdlc/model-council/, not a new assessment — no adapter is called, no tokens are spent, unless rebuild is given (still token-free, see step 3).

Arguments: $ARGUMENTS — optional literal rebuild.

Do this:

No roster yet? If .sdlc/model-council/roster.json doesn't exist, say so plainly and stop: point at /sdlc-model-council:council-commission (full onboarding: discover, characterize, audition, roster, policy) or /sdlc-model-council:council-assess (just the assessment) as the two ways to produce one. Don't fabricate a roster from priors here — that's what commission's skip audition choice is for.
Roster exists — present it. Show .sdlc/model-council/roster.md as-is (it already has the per-model table: grades, per-dimension posterior/n/ci95, roles, cost/item, p50 latency). Then read .sdlc/model-council/diversity.json and summarise its pairs array:
- Most decorrelated pair — lowest both_wrong_rate among pairs where insufficient is false — this is the best casting complement.
- Most correlated pair — highest both_wrong_rate (or any pair marked insufficient, which cast.py treats as maximally correlated by design — call these out separately, they're a data gap not a diversity finding). Reference the council-policy skill if the user asks what any of this means for routing — role assignment and casting rules live there, not in this command.

rebuild — re-derive the roster and diversity map from the existing .sdlc/model-council/results.jsonl without dispatching any model. This is for after a manual edit to results.jsonl, a pricing refresh, or a priors update — cheap and token-free because it only re-scores rows already on disk. Run:

${CLAUDE_PLUGIN_ROOT}/scripts/council/roster.py \
  --results .sdlc/model-council/results.jsonl \
  --priors-dir ${CLAUDE_PLUGIN_ROOT}/scripts/council/priors \
  --pricing ${CLAUDE_PLUGIN_ROOT}/scripts/council/pricing.json \
  --out-json .sdlc/model-council/roster.json \
  --out-md .sdlc/model-council/roster.md

${CLAUDE_PLUGIN_ROOT}/scripts/council/diversity.py \
  --results .sdlc/model-council/results.jsonl \
  --stack ${CLAUDE_PLUGIN_ROOT}/assessment/stack/v1/stack.json \
  --out .sdlc/model-council/diversity.json

Then present the rebuilt roster per step 2. If .sdlc/model-council/results.jsonl doesn't exist either, there's nothing to rebuild from — say so and point at council-assess/council-commission instead.

Staleness check. Compare the roster's generated_ts (.sdlc/model-council/roster.json) against the timestamps in .sdlc/model-council/assessment-log.jsonl — if any log entry's ts is newer than roster.json's generated_ts, the on-disk roster predates the latest assessment run. Flag this plainly and suggest rebuild (if results.jsonl already reflects the newer run) or a fresh /sdlc-model-council:council-assess (if it doesn't).

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.

10d ago First seen · 66 lines · 28 tokens per session scan A fb62708e94aa

Subscribe to this mod's changes

council-roster is a command published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 910 once invoked, about $0.0001 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.

Analytics and metrics Building agents

council-roster

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement