aristo: Instructions file for Claude Code

CLAUDE.md

aristo CLAUDE.md is an instructions file for Claude Code from aretta-ai/aristo. It costs 5,392 tokens per session, scanned A, original, MIT.

Repository working instructions for Aristo, covering commit size, commit-message format, changelog entries, and test-first development. Test-first development means writing a test before implementing the code it checks.

In plain words
What is it for?
Use it before changing Aristo code to decide how to split commits, name them, update the changelog, and demonstrate correctness with tests.
Why use it?
It gives contributors fixed rules for making changes that are easier to review, document, and verify.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is aretta-ai/aristo's own configuration. It tells Claude Code how to work on aristo 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 aristo configures →

Reuse

Borrowing it

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

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 aristo CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/aretta-ai/aristo/claude-md"><img src="https://agentmods.dev/badge/instructions/aretta-ai/aristo/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,392 This file is loaded in full into every session.
When invoked 5,392 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 $0.05392 $0.05392
Opus 5 $0.02696 $0.02696
Sonnet 5 $0.01078 $0.01078
Haiku 4.5 $0.00539 $0.00539

Measured 9d ago against content hash e87b233ce4de, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

aristo 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 9d 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 · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Aristo working agreement

This file is law. Every Claude Code session in this repo MUST read this file before touching code, and MUST obey every rule below. These rules are not aspirational — they are how we work. Violating any of them is grounds for the user to revert your change.

If you find yourself rationalizing an exception ("just this once," "the rule doesn't really apply here"), STOP. The rule applies. If the rule is genuinely wrong, surface that to the user and propose a CLAUDE.md edit — do not silently bypass it.


§1. Commit size — small or medium ONLY

  • Large commits are FORBIDDEN. No exceptions.
  • Heuristic: if the diff exceeds ~200 changed lines OR touches more than ~5 files for unrelated reasons, SPLIT IT.
  • One logical change per commit. If the message needs the word "and," it is two commits.
  • The only allowed "wide" commit is a mechanical, atomic refactor (e.g. a project-wide rename) that is trivially reviewable as a single operation. Surface these to the user before making them.

§2. Commit messages — semantic / conventional

Required prefix from this exact set:

Prefix Use for
feat: new user-visible functionality
fix: bug fix
refactor: code change that neither fixes a bug nor adds a feature
perf: performance improvement, no behavior change
docs: documentation only (including this file, README, CHANGELOG-only edits — but see §3)
test: tests only
build: build system, dependencies, Cargo.toml, workspace config
chore: housekeeping that doesn't fit above
ci: CI / GitHub Actions config

Optional scope in parens: feat(macros): ..., fix(cli): ..., build(workspace): ....

Banned messages: wip, stuff, updates, misc, fixes, progress, more changes. Say what changed.

§3. CHANGELOG.md — one line per commit, in the same commit

  • Every commit MUST add at least one bullet to the ## [Unreleased] section of CHANGELOG.md, describing what changed in customer-facing language.
  • The CHANGELOG bullet ships in the same commit as the code change. Never a separate "update changelog" commit.
  • Format: - <area>: <what changed and why a user cares>. Examples:
    • - macros: \#[aristo::intent]` now accepts multi-line text without escaping.`
    • - cli: \aristo verify --audit` exits non-zero on stale/refuted proofs for CI gating.`
  • At release: promote ## [Unreleased] to ## [vX.Y.Z] — YYYY-MM-DD. The [Unreleased] block must read coherently as a release-note draft when scanned end-to-end.

Read the full file on GitHub · 252 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. 9d ago First seen · 252 lines · 5,392 tokens per session scan A e87b233ce4de

Subscribe to this mod's changes

aristo CLAUDE.md is an instructions file published in the GitHub repository aretta-ai/aristo (51 stars, last pushed 1mo ago), licensed MIT. It adds 5,392 tokens to every session, about $0.0270 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 2026-08-30.

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,737 tokens