What is agent-council CLAUDE.md?

Project guidance for a command-line tool where several AI assistants discuss a question and reach a shared decision. It explains the project structure, testing approach, safety checks, and file storage patterns.

Use it when adding features, fixing bugs, testing, or understanding how the council coordinates Claude Code, Codex CLI, and Gemini CLI.

It helps developers work consistently in a project that runs multiple AI command-line programs at once. The guidance makes important behaviours, such as time limits and safe file handling, easier to preserve.

How yogirk/agent-council configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to yogirk/agent-council. 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/yogirk/agent-council/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/yogirk/agent-council

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/yogirk/agent-council/claude-md/github.svg)](https://agentmods.dev/instructions/yogirk/agent-council/claude-md)

Your own site

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

Per session 744 This file is loaded in full into every session.

When invoked 744 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	$0.00744	$0.00744
Opus 5.5	$0.00298	$0.00298
Sonnet 5.5	$0.00149	$0.00149
Haiku 4.5	$0.00074	$0.00074

Measured 2mo ago against content hash 797eeaf37c95, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-council 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 2mo 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 · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Council

Multi-agent deliberation tool. Convenes Claude Code, Codex CLI, and Gemini CLI to deliberate on questions.

Architecture

src/council.ts — CLI entry point, orchestration, subprocess dispatch, quorum logic, all subcommands
src/adapters.ts — Agent adapters (Claude, Codex, Gemini) + shared types (SessionMeta, AgentResult)
src/prompts.ts — Stage 1, 2, 3, 4 (nudge) prompt templates
src/viewer.ts — Self-contained HTML viewer generation (verdict-first, progressive depth, light/dark mode)
bin/council — Bun entry script
skills/claude-code/ — SKILL.md files for all slash commands (cross-platform compatible)
eval/ — Benchmark framework (10 questions, run-eval.ts)

Testing

Run: bun test Framework: Bun built-in test runner Fixtures: tests/fixtures/ — real CLI output from Claude, Codex, Gemini

Key patterns

buildContextBundle() has path traversal protection — validates all file paths
dispatchWithQuorum() handles parallel agent dispatch with per-agent timeouts and grace windows
writeJson() is async with atomic rename (write to .tmp, then rename)
detectChairman() auto-detects invoking CLI from environment signals
SKILL.md files use universal binary discovery (checks all CLI skill directories)
Viewer uses escapeJsonForScript() for XSS protection + textContent everywhere (no innerHTML)
main() is guarded from running during test imports
classifyError() returns typed ErrorClass for actionable error messages
preflightCheck() validates agent health (version + no-op prompt) before sessions
dispatchAgentWithRetry() retries transient failures (timeout, rate_limit) once
parseStructuredSections() uses fuzzy heading aliases for assumption/belief parsing
runNudge() dispatches Stage 4 correction to a single agent, saves to stage4/

Storage

Sessions: ~/.council/{project}/{session-id}/ Config: ~/.council/config.json

Config defaults

Claude: 120s timeout, Codex: 120s, Gemini: 180s
Quorum grace: 30s
Models: claude-opus-4-6, gpt-5.4, gemini-3.1-pro
Proactive nudges: true

Read the full file on GitHub · 67 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.

2mo ago First seen · 67 lines · 744 tokens per session scan A 797eeaf37c95

Subscribe to this mod's changes

agent-council CLAUDE.md is an instructions file published in the GitHub repository yogirk/agent-council (92 stars, last pushed 7mo ago), licensed MIT. It adds 744 tokens to every session, about $0.0030 per session on Opus 5.5. 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.

Building agents

agent-council CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent-council CLAUDE.mdyogirk/agent-council	Instructions file	92	7mo ago	MIT	A	744	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

agent-council: Instructions file for Claude Code