council

council is a skill for Claude Code, Codex from stoa-platform/stoa. It costs 31 tokens per session (4,707 once invoked), scanned A, original, Apache-2.0.

A review workflow that asks eight different reviewer roles to assess a feature or architecture decision record, then can create a Linear task when the score is high enough. An architecture decision record is a document explaining an important technical choice.

In plain words
What is it for?
Checking whether a ticket is worthwhile, validating a plan, scoring proposed changes, and reviewing implementation stages through the related scripts and checks.
Why use it?
It adds a structured challenge before implementation and connects an approved proposal to a tracked task.

Skill for Claude CodeCodex

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

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/stoa-platform/stoa/council.svg)](https://agentmods.dev/skills/stoa-platform/stoa/council)
Your own site
<a href="https://agentmods.dev/skills/stoa-platform/stoa/council"><img src="https://agentmods.dev/badge/skills/stoa-platform/stoa/council.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,707 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 $0.00031 $0.04707
Opus 5 $0.00015 $0.02354
Sonnet 5 $0.00006 $0.00941
Haiku 4.5 $0.00003 $0.00471

Measured 4d ago against content hash 5a89ee0ea42e, 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 4d 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/skills/council/SKILL.md · 403 lines

How it starts

The opening of the file, as written. The whole thing — 403 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Council Validation — $ARGUMENTS

Three-Stage Council

This skill drives Stage 1 (ticket pertinence) and Stage 2 (plan validation) — both prose-based, 8-persona scoring per the canonical Team Coca jury (HEG-PAT-003).

Stage 3 (code review) runs after implementation on the actual diff, via scripts/council-review.sh (4-axis: conformance, debt, attack_surface, contract_impact). It is not invoked by this skill — it is wired to the pre-push hook (CAB-2048) and council-gate.yml CI workflow (CAB-2049). See .claude/docs/council-s3.md for full docs.

S1 (this skill, prose)  →  S2 (this skill, plan)  →  implementation  →  S3 (council-review.sh, diff)  →  merge

Step 1: Gather Context

Read and understand the feature/ADR/change description. Gather context from:

  • memory.md — current sprint, related work
  • plan.md — where this fits in priorities
  • Relevant code files if technical

Step 1b: Context Compiler — Impact Score

Run the Context Compiler to get the blast radius before scoring:

  1. Determine the primary component from $ARGUMENTS (or from the ticket description if CAB-XXXX is provided)
  2. Run: docs/scripts/build-context.sh --component <component> --intent "$ARGUMENTS"
    • If a ticket ID is available: add --ticket "CAB-XXXX"
  3. Read the generated context pack in docs/context-packs/
  4. Extract the Impact Score and level (LOW/MEDIUM/HIGH/CRITICAL)
  5. Include the Impact Score in each persona's evaluation context
  6. If CRITICAL (>= 31): flag it explicitly in the Council report header

Read the full file on GitHub · 403 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. 4d ago First seen · 403 lines · 31 tokens per session scan A 5a89ee0ea42e

Subscribe to this mod's changes

council is a skill published in the GitHub repository stoa-platform/stoa (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 4,707 once invoked, about $0.0002 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.