council

council is a skill for Claude Code from chrisblattman/claudeblattman. It costs 55 tokens per session (2,011 once invoked), scanned A, original, MIT.

A review workflow that sends a plan, draft, or decision to several independent critic agents, then combines their findings in a separate review. The critics look at the proposal from different angles, such as evidence, failure risks, missing details, and cost.

In plain words
What is it for?
Use it to challenge plans, review drafts, assess decisions, identify likely failure points, and produce a combined critique.
Why use it?
It reduces the chance that one person or agent overlooks a serious assumption or risk. Separate critiques help prevent early opinions from shaping every later comment.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; mentions subagents; mentions Codex.

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 starter-kit plugin — 3 skills, 2 commands, 4 agents shipped together

Good fit Use it to challenge plans, review drafts, assess decisions, identify likely failure points, and produce a combined critique.

Compare 6 skills 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 chrisblattman/claudeblattman
Claude Code
/plugin install starter-kit

Made for: Claude Code.

Or install starter-kit, the plugin that ships this one along with the rest of its 3 skills, 2 commands, 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/skills/chrisblattman/claudeblattman/council/github.svg)](https://agentmods.dev/skills/chrisblattman/claudeblattman/council)
Your own site
<a href="https://agentmods.dev/skills/chrisblattman/claudeblattman/council"><img src="https://agentmods.dev/badge/skills/chrisblattman/claudeblattman/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/skills/chrisblattman/claudeblattman/council"><img src="https://agentmods.dev/badge/skills/chrisblattman/claudeblattman/council.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,011 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 $0.00055 $0.02011
Opus 5 $0.00028 $0.01006
Sonnet 5 $0.00011 $0.00402
Haiku 4.5 $0.00006 $0.00201

Measured 10d ago against content hash 818ec58f8e9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 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/starter-kit/skills/council/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/council — Parallel Critics, Then a Separate Synthesis

Dispatch 3–4 critic agents in parallel on the same input, collect their raw critiques, then run ONE synthesis pass in a fresh context. Hard cap: 4 critics. Single round only — critics speak once, the synthesizer reads once. Never turn the critiques into a majority vote.

Why this shape:

  • Parallel, not sequential — independent critics with different lenses catch different problems, and nobody anchors on whoever spoke first.
  • One round only — no debate or rebuttals. Multi-round AI debate drifts toward consensus, not accuracy.
  • Separate synthesis — a fresh-context pass reads the critiques as data instead of being swayed by the conversation that produced them.

The four shipped critics

Critic Lens
skeptic Wishful thinking — which load-bearing claims aren't backed by evidence?
pre-mortem Works backward from failure — the top 3 ways this fails
completeness-checker What's missing that a domain expert would expect?
chief-of-staff What's the actual decision, and what does saying yes cost the user?

Persona files live at ${CLAUDE_PLUGIN_ROOT}/agents/<name>.md.

Default panels

Task type Panel N
Plan / architecture / workflow review skeptic, pre-mortem, completeness-checker 3
Decision support ("should I…") skeptic, pre-mortem, chief-of-staff 3

Paper and grant-proposal panels need additional personas — future release. If the user asks for one, say so and offer the plan panel as the closest fit.

Inferring the type when --type isn't given: "plan / design / architecture / workflow" → plan; "should I / decide / go or no-go / accept or reject" → decision; unclear → ask one line: "Is this a plan review or a decision?"

When NOT to run a council

  • Quick lookups, single-file edits, casual brainstorming — just answer.
  • Inputs under ~50 words of substance — there isn't enough for three critics to disagree about. Offer a quick single review instead.
  • If it's unclear whether the user wants a council run or is just discussing councils as a topic, ask one line before dispatching.

Read the full file on GitHub · 129 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 · 129 lines · 55 tokens per session scan A 818ec58f8e9c

Subscribe to this mod's changes

council is a skill published in the GitHub repository chrisblattman/claudeblattman (452 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 2,011 once invoked, about $0.0003 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 2026-08-30.