mast: Instructions file for Claude Code

CLAUDE.md

mast CLAUDE.md is an instructions file for Claude Code from SpikedPunchVictim/mast. It costs 10,821 tokens per session, scanned A, original, MIT.

A set of instructions for coding agents working on the MAST project. It explains how to read the project’s architectural decisions and empirical findings before changing or re-running work.

In plain words
What is it for?
Guiding agent work in the MAST repository, including reading ADRs—written records of architectural decisions—and checking documented evaluation findings.
Why use it?
It helps prevent changes or repeated experiments that ignore documented decisions and prior results.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions subagents; positional $N argument.

This is SpikedPunchVictim/mast's own configuration. It tells Claude Code how to work on mast itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mast configures →

Reuse

Borrowing it

Nothing to install: this file belongs to SpikedPunchVictim/mast. 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/SpikedPunchVictim/mast/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/SpikedPunchVictim/mast

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.

agentmods badge for mast CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/spikedpunchvictim/mast/claude-md.svg)](https://agentmods.dev/instructions/spikedpunchvictim/mast/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/spikedpunchvictim/mast/claude-md"><img src="https://agentmods.dev/badge/instructions/spikedpunchvictim/mast/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 10,821 This file is loaded in full into every session.
When invoked 10,821 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.10821 $0.10821
Opus 5 $0.05411 $0.05411
Sonnet 5 $0.02164 $0.02164
Haiku 4.5 $0.01082 $0.01082

Measured 3d ago against content hash f041cbfed872, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mast 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 3d 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 · 769 lines

How it starts

The opening of the file, as written. The whole thing — 769 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file is the operating manual for Claude in this repository. Read it fully before responding to any request. The rules below are non-negotiable and override default behaviour, conversational shortcuts, or pattern-matched assumptions.

MAST was developed inside the kluster monorepo and split out on 2026-08-19. This file merges what were two documents there — kluster's .claude/CLAUDE.md (§1–§11, of which the Fastify conventions, the packages/kluster-bt rules and the /propose /dispatch /review agent framework did not travel) and packages/mast/CLAUDE.md (the defect-ledger manual, now the last section here). Both were loaded together when working in packages/mast, so nothing that governed this code has been dropped except what named kluster packages that no longer exist alongside it. See docs/provenance/.


Instructions

Decisions live in adr/

Every architectural and empirical decision is recorded as an ADR: adr/NNN-YYYY-MM-DD-<feature>.md, with supporting material under adr/proposals/<feature>/. Start at adr/README.md — it carries the index and a reading order, which is not the numeric order. adr/010-2026-08-11-empirical-method.md governs all empirical work and is the one to read first.

IMPLEMENTATION_PLAN.md is no longer the plan — it is a routing stub mapping every heading of the former 11,459-line document to its shard. Do not append to it. New work appends to the relevant ADR, or opens a new one (next number, today's date).

Empirical work in this repo — the findings index

FINDINGS.md is the consolidated index of every settled empirical claim, every refuted hypothesis, and every measurement that is recorded in a committed journal but read by no scorer. It is derived from the adr/proposals/*/PLAN-EXCERPT.md shards and the eval/results/ artifacts, and it is maintained in place.

  • Before writing any pre-registration, you MUST read FINDINGS.md §1 (unread data) and §3 (dead hypotheses), and state in the registration what you checked and what you found. A registration that does not do this is incomplete.
  • When a RESULT block lands in a PLAN-EXCERPT.md shard, update FINDINGS.md in the same commit. Headline verdict to §2; any refuted hypothesis to §3, with the number that killed it.
  • When a new journal is committed, re-run the §1 diff — enumerate the keys in every eval/results/*-runs.jsonl, grep the scorers for each — and update the register of unread data.
  • The PLAN-EXCERPT.md shards remain authoritative and append-only. FINDINGS.md is a derived index and is edited in place. If the two disagree, the shards and the scored artifacts win.
  • Eval scripts stay in eval/. They are not moved into proposal directories — see ADR 001. Each decision's instruments are listed in adr/proposals/<feature>/EVAL.md.

Read the full file on GitHub · 769 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. 3d ago Changed · +10 lines · +329 tokens per session f041cbfed872
  2. 7d ago First seen · 759 lines · 10,492 tokens per session scan A 6ce7091b1af2

Subscribe to this mod's changes

mast CLAUDE.md is an instructions file published in the GitHub repository SpikedPunchVictim/mast (0 stars, last pushed 3d ago), licensed MIT. It adds 10,821 tokens to every session, about $0.0541 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

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

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens