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.
npx agentmods add instructions/dataviking-tech/althing/claude-mdgit clone --depth 1 https://github.com/DataViking-Tech/AlthingWhat 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 | $0.01929 | $0.01929 |
| Opus 5 | $0.00964 | $0.00964 |
| Sonnet 5 | $0.00386 | $0.00386 |
| Haiku 4.5 | $0.00193 | $0.00193 |
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.
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
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.
- yesterday First seen · 199 lines · 1,929 tokens per session scan A 1af43971c9ea
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.
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.
agenda-intelligence-md CLAUDE.md
Instructions for vassiliylakhonin/agenda-intelligence-md, covering claude code working rules, before push and working style in this repo.
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.
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…
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.
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.