matrixscroll: Instructions file for Claude Code

CLAUDE.md

matrixscroll CLAUDE.md is an instructions file for Claude Code from SSX360/matrixscroll. It costs 813 tokens per session, scanned A, original, Apache-2.0.

Repository-wide writing instructions for matrixscroll. They define the required voice, sentence style, naming rules, banned words, and a Vale check, where Vale is a tool that finds writing problems.

In plain words
What is it for?
Use them when writing or reviewing matrixscroll documentation, headings, instructions, and other prose. Run Vale with the stated error threshold before starting and finishing.
Why use it?
They keep the repository’s documentation consistent and require automated checks before and after editing. They also prevent vague wording and specific forbidden terms.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is SSX360/matrixscroll's own configuration. It tells Claude Code how to work on matrixscroll 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 matrixscroll configures →

Reuse

Borrowing it

Nothing to install: this file belongs to SSX360/matrixscroll. 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/SSX360/matrixscroll/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/SSX360/matrixscroll

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 matrixscroll CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ssx360/matrixscroll/claude-md/github.svg)](https://agentmods.dev/instructions/ssx360/matrixscroll/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ssx360/matrixscroll/claude-md"><img src="https://agentmods.dev/badge/instructions/ssx360/matrixscroll/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.

agentmods 80×15 button for matrixscroll CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ssx360/matrixscroll/claude-md"><img src="https://agentmods.dev/badge/instructions/ssx360/matrixscroll/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 813 This file is loaded in full into every session.
When invoked 813 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 $0.00813 $0.00813
Opus 5.5 $0.00325 $0.00325
Sonnet 5.5 $0.00163 $0.00163
Haiku 4.5 $0.00081 $0.00081

Measured 1mo ago against content hash 02ba9128006e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

matrixscroll 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 1mo 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 · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prose rules

Read these rules before editing user-facing text. The style supplement defines terminology. The ssx360-prose skill provides additional guidance.

Run Vale before editing and again before publishing. The linter checks prose patterns. Source review and workflow tests establish whether the claims and instructions are supported.

Voice and structure

Use active voice, sentence-case headings and present tense. Address the reader directly in instructions. Name a concrete command, field, version, date or source in each paragraph.

Use periods, commas or parentheses instead of em dashes and en-dash separators. Use a hyphen for numeric ranges. Keep negative parallelism to one deliberate instance per page. Retired AP2 mandate-chain slogans stay retired.

Prohibited wording

Avoid these words and phrases in public copy:

seamless, seamlessly, cutting-edge, robust, game-changer, unleash, elevate,
next-gen, revolutionize, delve, tapestry, leverage, harness, empower,
state-of-the-art, best-in-class, world-class, paradigm shift, supercharge,
frictionless, turnkey, holistic, synergy, bleeding-edge, military-grade,
bulletproof, future-proof, in today's landscape, the future of, deep dive,
rapidly evolving, it is important to note that, it should be noted that,
in order to, utilize, prior to

Gold standard

The gold-standard policy governs protocol, crypto, verification, gates and public claims. Preserve the required code-owner review and source-traceable evidence.

Do not land AI-generated or AI-altered bytes as authority in the verified core: vectors, ACVP fixtures, TLA+ models, schemas and SPEC. Digest-pin provenance. No AI system decides a technical conclusion.

Preserve fail-closed CONSISTENT, INDETERMINATE and INCONSISTENT verdicts with exit codes 0, 1 and 2. No silent pass on missing evidence. Do not claim an extracted Lean 4 or F* verifier until it exists in the tree.

Read the full file on GitHub · 83 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. 1mo ago Changed · -16 lines · -224 tokens per session 02ba9128006e
  2. 1mo ago Changed · +10 lines · +107 tokens per session b5137cf339e2
  3. 1mo ago Changed · +2 tokens per session 978c35f58a80
  4. 2mo ago First seen · 89 lines · 928 tokens per session scan A fa648e485d33

Subscribe to this mod's changes

matrixscroll CLAUDE.md is an instructions file published in the GitHub repository SSX360/matrixscroll (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 813 tokens to every session, about $0.0033 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 2026-08-31.

Related

matrixscroll CLAUDE.md compared with instructions from other repositories

matrixscroll CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
matrixscroll CLAUDE.mdSSX360/matrixscrollInstructions file51mo agoApache-2.0A813Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode