council

council is a skill for Claude Code, Codex from adonai-labs/agent-runway. It costs 88 tokens per session (1,069 once invoked), scanned A, original, MIT.

A lightweight review process that examines an idea, assumption, or proposed technical approach from several viewpoints before development begins. It is intended to inform decisions before creating a specification, ticket, architecture decision record, or code change.

In plain words
What is it for?
Use it to review ideas, test hypotheses, and assess implementation approaches before investing in detailed planning or coding.
Why use it?
It helps expose weak assumptions, risks, and missing considerations early. The review can support a decision to continue, revise, pause, or reject the proposal.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review ideas, test hypotheses, and assess implementation approaches before investing in detailed planning or coding.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adonai-labs/agent-runway/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 adonai-labs/agent-runway --skill council
Clone the repo
git clone --depth 1 https://github.com/adonai-labs/agent-runway

Made for: Claude Code, Codex.

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/adonai-labs/agent-runway/council/github.svg)](https://agentmods.dev/skills/adonai-labs/agent-runway/council)
Your own site
<a href="https://agentmods.dev/skills/adonai-labs/agent-runway/council"><img src="https://agentmods.dev/badge/skills/adonai-labs/agent-runway/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/adonai-labs/agent-runway/council"><img src="https://agentmods.dev/badge/skills/adonai-labs/agent-runway/council.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,069 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 $0.00088 $0.01069
Opus 5 $0.00044 $0.00535
Sonnet 5 $0.00018 $0.00214
Haiku 4.5 $0.00009 $0.00107

Measured 10d ago against content hash f33d44cf0158, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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.

src/core/skills/council/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Council

Invoke Skill

@council <idea, hypothesis, or implementation direction>

Examples:

  • @council should we add workspace memory to the Lite preset?
  • @council hypothesis: users want checkpoints more than full specs
  • @council validate this implementation approach before I code it

This skill is preview. Keep the output useful and compact; expect the exact format to evolve as real usage exposes better lenses.


What this skill does

Runs a lightweight multi-perspective review before the work becomes a spec, ticket, ADR, or implementation.

Use it to decide whether to pursue, refine, pause, or reject an idea. Do not use it as a replacement for @code-review, @architect, @spec-creator, or @lead.


Workflow

1. Capture the proposition

Restate the idea in one sentence.

If the proposition is too vague to evaluate, ask at most one clarifying question. Otherwise, state assumptions and continue.

Classify the input as one of:

Type Meaning
Idea A possible feature, workflow, product change, or user-facing capability
Hypothesis A belief that needs evidence before investment
Implementation A proposed technical path or design direction

2. Review through six lenses

Evaluate only what can be inferred from the provided context and observable project state.

Lens Question
Product Does this solve a real user problem or sharpen positioning?
Engineering Is the complexity proportional to the expected value?
Architecture Does it fit the system shape without locking in a bad abstraction?
Risk/Security What could break, leak, confuse, or create unsafe behavior?
Adoption Will target users understand when and how to use it?
Contrarian What is the strongest reason not to do it?

3. Return a verdict

Use exactly one:

  • Pursue: valuable, clear enough, and low enough risk to proceed
  • Refine: promising, but scope or behavior must be sharpened first
  • Pause: not enough evidence yet; run an experiment or gather signal
  • Reject: likely not worth building or actively harmful to the product

Read the full file on GitHub · 152 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 · 152 lines · 88 tokens per session scan A f33d44cf0158

Subscribe to this mod's changes

council is a skill published in the GitHub repository adonai-labs/agent-runway (2 stars, last pushed 20d ago), licensed MIT. It adds 88 tokens to every session and 1,069 once invoked, about $0.0004 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.