What is ai-counsel CLAUDE.md?

A set of repository instructions describing the AI Counsel project's structure, components, data flow, and development expectations.

Use it when working on the AI Counsel MCP server, including its deliberation engine, tools, validation, logging, and tests.

It gives a coding agent the project context needed to make changes that fit the existing architecture and conventions.

How blueman82/ai-counsel configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to blueman82/ai-counsel. 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/blueman82/ai-counsel/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/blueman82/ai-counsel

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/blueman82/ai-counsel/claude-md/github.svg)](https://agentmods.dev/instructions/blueman82/ai-counsel/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/blueman82/ai-counsel/claude-md"><img src="https://agentmods.dev/badge/instructions/blueman82/ai-counsel/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/blueman82/ai-counsel/claude-md"><img src="https://agentmods.dev/badge/instructions/blueman82/ai-counsel/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 6,472 This file is loaded in full into every session.

When invoked 6,472 The same file — it is already loaded in full.

Security scan B 1 finding. 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	$0.06472	$0.06472
Opus 5.5	$0.02589	$0.02589
Sonnet 5.5	$0.01294	$0.01294
Haiku 4.5	$0.00647	$0.00647

Measured 26d ago against content hash e51278a7eec4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

ai-counsel CLAUDE.md scanned grade B with 1 finding 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 26d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **Production**: Configure in `~/.claude/config/mcp.json`, check `mcp_server.log` for debugging

CLAUDE.md · 507 lines

How it starts

The opening of the file, as written. The whole thing — 507 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Last updated: 2026-02-15
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

AI Counsel: MCP server; multi-model debate; shared prior responses; iterative consensus.
Key differentiation: Models engage in actual debate with cross-pollination (not just parallel aggregation).
Production Ready: 113+ passing tests, type-safe validation, graceful error handling, structured logging, convergence detection, AI-powered summaries, evidence-based deliberation with secure tool execution.

Architecture

Core Components

MCP Server Layer (server.py)
Entry point for MCP protocol communication via stdio
Exposes 2 MCP tools: deliberate and query_decisions (when decision graph enabled)
Handles JSON serialization and response truncation for token limits
Logs to mcp_server.log (not stdout/stderr to avoid stdio interference)
Deliberation Engine (deliberation/engine.py)
Orchestrates multi-round debates between models
Manages context building from previous responses
Coordinates convergence detection and early stopping
Initializes AI summarizer with fallback chain: Claude Sonnet → gpt-6.1-sol → Droid → Gemini
Integrates tool execution system for evidence-based deliberation
Tool Execution System (deliberation/tools.py, models/tool_schema.py)
Base: BaseTool with execute() method and security controls
Tools: ReadFileTool (configurable size limit), SearchCodeTool, ListFilesTool, RunCommandTool (whitelist: ls, grep, find, cat, head, tail), GetFileTreeTool (ASCII output for clean JSON)
Orchestrator: ToolExecutor parses TOOL_REQUEST markers, validates, routes to tools
Security: Whitelisted commands, file size limits, timeout protection (10s default), path exclusion patterns (prevents context contamination)
Path Exclusions: Configurable patterns to block access to sensitive directories (e.g., transcripts/, .git/, node_modules/)
File Tree Rendering: Uses ASCII characters (|--) in tool responses for clean JSON serialization; Unicode box-drawing (├──) in Round 1 prompts for better readability
Context injection: Tool results visible to all participants in subsequent rounds

Read the full file on GitHub · 507 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.

26d ago Changed · -75 tokens per session e51278a7eec4
2mo ago First seen · 507 lines · 6,547 tokens per session scan B 30e3e93ebee5

Subscribe to this mod's changes

ai-counsel CLAUDE.md is an instructions file published in the GitHub repository blueman82/ai-counsel (1 stars, last pushed 27d ago), licensed MIT. It adds 6,472 tokens to every session, about $0.0259 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

ai-counsel CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ai-counsel CLAUDE.mdblueman82/ai-counsel	Instructions file	1	27d ago	MIT	B	6,472	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

ai-counsel: Instructions file for Claude Code