council

council is a command for Claude Code from ANcpLua/ancplua-claude-plugins. It costs 94 tokens per session (1,886 once invoked), scanned A, original, MIT.

A command that starts a coordinated AI team for a complex research question. A captain gathers cited information, a synthesizer reasons over it, and a clarity reviewer checks for missing or unclear parts.

In plain words
What is it for?
Use it when a task needs cited evidence, careful reasoning, and live checking between agents. Claude Code's experimental agent-team setting must be enabled.
Why use it?
It combines research with a second review pass, helping expose gaps before the answer is delivered.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

Part of the council plugin — 1 command, 4 agents shipped together

Good fit Use it when a task needs cited evidence, careful reasoning, and live checking between agents. Claude Code's experimental agent-team setting must be enabled.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ancplua/ancplua-claude-plugins/council
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.

Clone the repo
git clone --depth 1 https://github.com/ANcpLua/ancplua-claude-plugins

Made for: Claude Code.

Or install council, the plugin that ships this one along with the rest of its 1 command, 4 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

README.md
[![agentmods](https://agentmods.dev/badge/commands/ancplua/ancplua-claude-plugins/council/github.svg)](https://agentmods.dev/commands/ancplua/ancplua-claude-plugins/council)
Your own site
<a href="https://agentmods.dev/commands/ancplua/ancplua-claude-plugins/council"><img src="https://agentmods.dev/badge/commands/ancplua/ancplua-claude-plugins/council/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

Your own site · 80×15
<a href="https://agentmods.dev/commands/ancplua/ancplua-claude-plugins/council"><img src="https://agentmods.dev/badge/commands/ancplua/ancplua-claude-plugins/council.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,886 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 $0.00094 $0.01886
Opus 5 $0.00047 $0.00943
Sonnet 5 $0.00019 $0.00377
Haiku 4.5 $0.00009 $0.00189

Measured 8d ago against content hash 5698260a7260, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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/council.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/council [task]

Invoke the council on [task].

Requirements

Agent teams are experimental and disabled by default. This command needs them:

{ "env": { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" } }

Without it, no team is set up at session start, and the lead can neither spawn teammates nor propose them. Check this first and fail loudly — a silent fallback to fire-and-forget subagents removes the synthesizer↔clarity cross-talk that is the entire point of the council.

When to use

  • Question requires both cited evidence (research) and rigorous reasoning (logic)
  • Answer needs gap-checking before delivery
  • Task is complex enough that a single pass will miss something
  • You want the synthesis reconciled live against the evidence before it ships

How it runs

captain = the session lead (Fable 5) — frames a research question
  │
  └── /deep-research <question>  (dynamic workflow — fans out searches, returns a cited report)
        │
        └── captain spawns teammates; the team forms on the first spawn
              │
              ├── synthesizer (Opus 5 teammate) reasons over the report + task
              └── clarity     (Opus 5 teammate) gap-checks the synthesis against the report
                    → asks synthesizer live follow-ups via SendMessage
                    → synthesizer responds in real time (reactive cross-pollination)
              │
              └── captain reads report + team messages → produces draft
                    │
                    └── janitor (Opus 5 teammate) → BLOAT_FLAG + CUTS via SendMessage
                          │
                          └── captain removes cuts → final output
                          │
                          └── shutdown requests; team dirs cleaned up on session exit

/deep-research is a dynamic workflow, not a live SendMessage teammate — it returns a report. The live cross-pollination is between the synthesizer and clarity reconciling that report.

Orchestration

Read the full file on GitHub · 150 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. 8d ago First seen · 150 lines · 94 tokens per session scan A 5698260a7260

Subscribe to this mod's changes

council is a command published in the GitHub repository ANcpLua/ancplua-claude-plugins (5 stars, last pushed 22d ago), licensed MIT. It adds 94 tokens to every session and 1,886 once invoked, about $0.0005 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.