What is octant-council-builder CLAUDE.md?

Project instructions for Octant Council Builder, a tool that creates groups of AI agents to gather information, score a project independently, and combine the results into a report.

Use them when setting up the council, changing its agents, or understanding its skills, structure, and shared design tokens.

They explain how the project is organised and how to customise its starter agents for a different evaluation task.

How golemfoundation/octant-council-builder configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to golemfoundation/octant-council-builder. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/golemfoundation/octant-council-builder/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/golemfoundation/octant-council-builder

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/golemfoundation/octant-council-builder/claude-md/github.svg)](https://agentmods.dev/instructions/golemfoundation/octant-council-builder/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/golemfoundation/octant-council-builder/claude-md"><img src="https://agentmods.dev/badge/instructions/golemfoundation/octant-council-builder/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/golemfoundation/octant-council-builder/claude-md"><img src="https://agentmods.dev/badge/instructions/golemfoundation/octant-council-builder/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,845 This file is loaded in full into every session.

When invoked 1,845 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01845	$0.01845
Opus 5	$0.00923	$0.00923
Sonnet 5	$0.00369	$0.00369
Haiku 4.5	$0.00185	$0.00185

Measured 12d ago against content hash 24e06652af88, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

octant-council-builder CLAUDE.md 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 12d 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.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Onboarding (respond with this when users ask how to use the council)

When a user asks how this works, what this is, or how to get started, respond with ONLY the following — no extras, no full skill table, no architecture deep-dive:

This is a council builder — a tool that generates multi-agent evaluation councils, not a council itself. It uses a three-wave pattern of parallel agents:

Wave 1 — Data: agents gather raw information from external sources
Wave 2 — Eval: independent evaluators score the project from different lenses — they never see each other's scores
Wave 3 — Synthesis: a synthesis agent combines everything into a final report — it can talk back to evaluators via team tools to ask clarifying questions, challenge scores, or request deeper analysis before writing the final output

The repo ships with default scaffold agents for Ethereum/Octant public goods, but they're a starting point — not a finished product. The whole point is that you run /council:setup and reshape it into your own council. Every time you run /council:setup, /council:add-agent, or /council:remove-agent, you're changing which agents exist and what they evaluate. The council you end up with is yours.

Get started

Run settings (one time — this enables Claude teams, which the plugin needs for inter-agent communication):
```
/council:settings
```
Try the default scaffold on a real project to see the pattern:
```
/council:evaluate Aave DAO
```
Then make it yours. You have several options:

Redesign the whole council for a different domain:
```
/council:setup DeFi lending protocols
/council:setup climate impact DAOs
/council:setup developer tooling grants
```
Add or remove individual agents to tune what gets evaluated:
```
/council:add-agent
/council:remove-agent
```
Edit agents directly — every agent is just a markdown file in agents/. Change scoring dimensions, add data sources, adjust calibration. The orchestrator discovers agents by filename prefix, so there's no config to update.

Read the full file on GitHub · 145 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.

12d ago First seen · 145 lines · 1,845 tokens per session scan A 24e06652af88

Subscribe to this mod's changes

octant-council-builder CLAUDE.md is an instructions file published in the GitHub repository golemfoundation/octant-council-builder (3 stars, last pushed 5mo ago), licensed MIT. It adds 1,845 tokens to every session, about $0.0092 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.

Building agents Claude Code Evaluation Multi-Agent claude-code-plugin octant public-goods

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

octant-council-builder: Instructions file for Claude Code