Althing CLAUDE.md

Project instructions for Althing, a Python tool that runs simulated focus groups using AI-generated participants. It also describes its language-model connections, session handling, parallel execution, structured responses, and cost tracking.

In plain words
What is it for?
Use it when developing, running, or changing Althing, including its model providers, agent sessions, saved sessions, and research panels.
Why use it?
It gives a coding agent the project context and operating details needed to work safely in the Althing codebase.

Instructions file

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 instructions/dataviking-tech/althing/claude-md
Clone the repo
git clone --depth 1 https://github.com/DataViking-Tech/Althing
Per session 1,929 This file is loaded in full into every session.
When invoked 1,929 The same file — it is already loaded in full.
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 $0.01929 $0.01929
Opus 5 $0.00964 $0.00964
Sonnet 5 $0.00386 $0.00386
Haiku 4.5 $0.00193 $0.00193

Measured yesterday against content hash 1af43971c9ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Althing 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 yesterday.

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 · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

althing

A lightweight, LLM-agnostic research harness for running synthetic focus groups using AI personas.

Architecture

Pure Python 3.10+ with minimal dependencies (httpx for HTTP, pyyaml for YAML parsing). Optional deps: mcp (MCP server).

src/althing/
├── llm/                  # Provider-agnostic LLM client
│   ├── client.py         # Unified send/stream interface
│   ├── aliases.py        # Model alias resolution (sonnet → claude-sonnet-4-6)
│   ├── errors.py         # Error types and retry logic
│   ├── models.py         # Data models (CompletionRequest, CompletionResponse, etc.)
│   └── providers/        # Provider implementations
│       ├── anthropic.py  # Claude
│       ├── openai_compat.py  # OpenAI, local models
│       ├── xai.py        # Grok
│       └── gemini.py     # Google Gemini
├── runtime.py            # Agent session loop (turns, tool calls, compaction)
├── orchestrator.py       # Parallel panelist execution (ThreadPoolExecutor)
├── structured/           # Schema-validated responses via tool-use forcing
├── cost.py               # Token tracking, model pricing, budget enforcement
├── persistence.py        # Session save/load/fork (JSON + JSONL)
├── plugins/              # Manifest-based extension system with hooks
├── instrument.py         # v1/v2/v3 instrument parser + DAG validator
├── routing.py            # v3 router predicates (contains/equals/matches)
├── mcp/                  # MCP server (12 tools, stdio transport)
│   ├── server.py         # MCP server entry point
│   └── data.py           # Persona + instrument pack and result persistence
├── packs/instruments/    # 5 bundled v3 branching instrument packs
├── cli/                  # CLI framework
│   ├── parser.py         # argparse setup
│   ├── commands.py       # Subcommand handlers (prompt, panel run)
│   ├── repl.py           # Interactive REPL
│   ├── slash.py          # Slash command registry
│   └── output.py         # Output formatting (text, json, ndjson)
└── main.py               # Entry point

Read the full file on GitHub · 199 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. yesterday First seen · 199 lines · 1,929 tokens per session scan A 1af43971c9ea

Subscribe to this mod's changes

Althing CLAUDE.md is an instructions file published in the GitHub repository DataViking-Tech/Althing (2 stars, last pushed 23d ago), licensed MIT. It adds 1,929 tokens to every session, about $0.0096 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.

Related

Other instructions, from other repositories

agenda-intelligence-md AGENTS.md

Instructions for vassiliylakhonin/agenda-intelligence-md, covering agents.md, project identity, relationship to the broader stack, product focus and vertical workers inside this repo and geography routing.

vassiliylakhonin/agenda-intelligence-md · 3,243 tokens

agenda-intelligence-md CLAUDE.md

Instructions for vassiliylakhonin/agenda-intelligence-md, covering claude code working rules, before push and working style in this repo.

vassiliylakhonin/agenda-intelligence-md · 399 tokens

deepagents AGENTS.md

AGENTS.md instructions for langchain-ai/deepagents, covering global development guidelines for the deep agents monorepo, corridor security analysis, development workflow, suppressing ruff rules and pr conventions.

langchain-ai/deepagents · 2,268 tokens

autoharness AGENTS.md

Instructions for tigerless-labs/autoharness: This repo uses Open Knowledge — collaborative markdown via MCP. .open-knowledge/config.yml (with optional /.open-knowledge/config.yml; CLI/env may override) is the path contract: content.dir is the root for relative paths; content.include lists globs that add markdown…

tigerless-labs/autoharness · 2,201 tokens

cookiecutter-mlops-package AGENTS.md

Instructions for fmind/cookiecutter-mlops-package, covering agents.md, project overview, setup & core commands, definition of done and conventions & idioms.

fmind/cookiecutter-mlops-package · 1,296 tokens

python-cheatsheet copilot-instructions.md

Copilot instructions for labex-labs/python-cheatsheet, covering python cheatsheet - ai coding assistant instructions, project overview, architecture & key patterns, content structure and routing & layout system.

labex-labs/python-cheatsheet · 1,155 tokens