council

council is a skill for Claude Code from larsboes/Axon. It costs 140 tokens per session (1,448 once invoked), scanned A, original, MIT.

A structured discussion among four or five subagents that take different positions on one decision. It runs one or more rounds and reports a recommendation together with the position that lost.

In plain words
What is it for?
Use it for architecture, investment, or other choices where alternatives need to be weighed, with a shorter check for decisions that are easy to reverse.
Why use it?
It makes important choices less dependent on one viewpoint and exposes trade-offs before a decision is made. It is for comparing options, not for attacking only one proposal.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the deliberation plugin — 4 skills, 7 agents shipped together

Good fit Use it for architecture, investment, or other choices where alternatives need to be weighed, with a shorter check for decisions that are easy to reverse.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/larsboes/axon/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.

Any agent
npx skills add larsboes/Axon --skill council
Clone the repo
git clone --depth 1 https://github.com/larsboes/Axon

Made for: Claude Code.

Or install deliberation, the plugin that ships this one along with the rest of its 4 skills, 7 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/larsboes/axon/council/github.svg)](https://agentmods.dev/skills/larsboes/axon/council)
Your own site
<a href="https://agentmods.dev/skills/larsboes/axon/council"><img src="https://agentmods.dev/badge/skills/larsboes/axon/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/larsboes/axon/council"><img src="https://agentmods.dev/badge/skills/larsboes/axon/council.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 140 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,448 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 $0.00140 $0.01448
Opus 5 $0.00070 $0.00724
Sonnet 5 $0.00028 $0.00290
Haiku 4.5 $0.00014 $0.00145

Measured 9d ago against content hash ac9545f7dd4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-15, 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 9d 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.

Packs/deliberation/skills/council/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

council

A council is four to five subagents that hold different positions on one decision. Each round runs them in parallel and feeds every member the rounds before it. The run ends with one recommendation and the position that lost.

Council weighs options against each other. To attack a single proposal, use red-team.

Adapted from the Council skill in LifeOS by Daniel Miessler (https://github.com/danielmiessler/LifeOS), MIT.

Procedure

Copy this checklist and track progress:

- [ ] 1. State the decision in one sentence
- [ ] 2. Pick DEBATE or QUICK
- [ ] 3. Pick a preset, or compose a council
- [ ] 4. Collect the evidence the members need
- [ ] 5. Run the rounds
- [ ] 6. Check every round with the clerk
- [ ] 7. Write the synthesis

1 — State the decision. Write the question the council answers and the options on the table. A question with one factual answer is not a council topic. Answer it directly and stop.

2 — Pick the mode.

Mode Rounds Use when
QUICK 1 The decision is cheap to reverse, or the caller wants a sanity check
DEBATE 3 The decision is expensive to reverse, or the options are close

Default to QUICK. Escalate to DEBATE when the members disagree about facts, not about taste.

3 — Pick a preset. Read the one file that matches the topic. Do not read the others.

Preset Decides File
architecture Placement, boundaries, adopt against build references/presets/architecture.md
investment A change to a personal portfolio references/presets/investment.md
travel One trip option against another references/presets/travel.md
security Threat model, data classes, blast radius references/presets/security.md
product What to build next, and how much of it references/presets/product.md

If no preset fits, read references/compose.md and write the briefs there. If the caller names the members, use those names and skip this step.

Never launch the same brief twice. Identical members agree, and agreement carries no information.

Read the full file on GitHub · 107 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 107 lines · 140 tokens per session scan A ac9545f7dd4e

Subscribe to this mod's changes

council is a skill published in the GitHub repository larsboes/Axon (1 stars, last pushed yesterday), licensed MIT. It adds 140 tokens to every session and 1,448 once invoked, about $0.0007 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 2026-09-07.