council

council is a command for Claude Code from SarutobiSasuke8/agentops-template. It costs 9 tokens per session (354 once invoked), scanned A, original, MIT.

A command that asks several specialized agent personas to review a project or a specific question in parallel, then combines their advice.

In plain words
What is it for?
Use it for a targeted task or question, or for a broader project review covering direction, technical health, risks, and delivery. It reads the project’s review rules and routes work to the relevant personas.
Why use it?
It brings different types of review to the same decision and helps match reviewers to the risks in scope.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/sarutobisasuke8/agentops-template/council
Clone the repo
git clone --depth 1 https://github.com/SarutobiSasuke8/agentops-template

Made for: Claude Code.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/sarutobisasuke8/agentops-template/council.svg)](https://agentmods.dev/commands/sarutobisasuke8/agentops-template/council)
Your own site
<a href="https://agentmods.dev/commands/sarutobisasuke8/agentops-template/council"><img src="https://agentmods.dev/badge/commands/sarutobisasuke8/agentops-template/council.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 354 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00009 $0.00354
Opus 5 $0.00005 $0.00177
Sonnet 5 $0.00002 $0.00071
Haiku 4.5 $0.00001 $0.00035

Measured 5d ago against content hash dde43081afd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

council 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 5d 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.

.claude/commands/council.md · 16 lines

What it actually says

Read personas/agent-council-protocol.md and AGENTS.md.

If a specific task or question was provided: Route through the minimum set of personas that covers the risk — do not invoke every role for a narrow task. Use the routing table in personas/agent-council-protocol.md to decide which roles are relevant.

If no task or question was provided: Run a full project review and advisory session. Read docs/PROJECT_BRIEF.md, ROADMAP.md, and TODO.md to load project context. Then route through all relevant council roles to produce a holistic review of the project's current state — covering product direction, technical health, open risks, delivery posture, and recommended next actions.

Execution — fan out via subagents: Each persona has a subagent in .claude/agents/ (see the mapping table in docs/SUBAGENTS.md). Launch the selected personas as parallel subagents in a single message. Give each one: the mission and success criteria, the specific files / diff / question in scope, and the compact council report format from personas/agent-council-protocol.md. Subagents cannot see this conversation — the prompt must be self-contained.

You are the conductor: synthesize the returned reports into one council report using the format in the protocol, resolving conflicts with its conflict-resolution order. Do not paste the raw subagent reports back-to-back.

Fallback: If subagents are unavailable, apply the persona files sequentially in-context (check personas/optional/ for any persona not in personas/) and synthesize the same way.

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. 5d ago First seen · 16 lines · 9 tokens per session scan A dde43081afd5

Subscribe to this mod's changes

council is a command published in the GitHub repository SarutobiSasuke8/agentops-template (9 stars, last pushed 16d ago), licensed MIT. It adds 9 tokens to every session and 354 once invoked, about $0.0000 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 2026-08-31.