spotless: Instructions file for Codex

AGENTS.md

spotless AGENTS.md is an instructions file for Codex, OpenCode from ripgrim/spotless. It costs 1,481 tokens per session, scanned A, original, MIT.

Project instructions for Spotless, a single-folder tool that sorts downloaded files into subfolders by file type and download source.

In plain words
What is it for?
Use them when modifying Spotless code, deciding where new logic belongs, or checking that changes follow the project's boundaries.
Why use it?
They give contributors the rules for changing the tool safely, including its architecture, naming, comments, and type-safety requirements.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is ripgrim/spotless's own configuration. It tells Codex and OpenCode how to work on spotless 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 spotless configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ripgrim/spotless. 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/ripgrim/spotless/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/ripgrim/spotless

Made for: Codex, OpenCode.

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 spotless AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ripgrim/spotless/agents-md"><img src="https://agentmods.dev/badge/instructions/ripgrim/spotless/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,481 This file is loaded in full into every session.
When invoked 1,481 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.01481 $0.01481
Opus 5.5 $0.00592 $0.00592
Sonnet 5.5 $0.00296 $0.00296
Haiku 4.5 $0.00148 $0.00148

Measured 2mo ago against content hash 693347c40974, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

spotless AGENTS.md scanned grade A with 1 finding 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 2mo 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

`spawnSync`-style call forms to be narrower than Node's.
AGENTS.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spotless, root agent rules

Read this before changing anything. The conventions below are carried over from ~/code/v2 and adapted: that repo is a TypeScript monorepo, this is a Native SDK app, so the discipline transfers and the specifics do not. Copying v2's stack rules verbatim here would be the exact slop they exist to prevent.

Mission

Spotless files new downloads into subfolders, by extension and by where the file was downloaded from. It is a single-folder tool: it reads one directory, moves files within it, and never deletes anything.

The dependency arrows (enforced by the compiler, not a script)

src/shared.ts      ← core + services   (boundary records only; imports nothing)
src/bytes.ts       ← core              (byte primitives)
src/rules.ts       ← core              (the rule table + pure helpers)
src/editing.ts     ← core              (the text-field reducer)
src/core.ts        ← the views          (Model, Msg, update, derived bindings)
src/services/*.ts  ← NOBODY            (reached only through @native-sdk/services)

The core never imports a service, even import type. That is NS1065 and the checker stops the build. Services may import subset-legal declarations from the core class; every record that crosses the boundary is declared once in src/shared.ts and nowhere else.

update is pure and synchronous. It never touches the filesystem: it returns a Cmd and the runtime dispatches the result back as a Msg.

Naming

  • .ts files kebab-case; .native view files named for their window label (src/windows/settings.native is the window whose label is settings).
  • Model fields and Msg kinds keep their TypeScript spellings, because markup binds them verbatim. A rename is a two-file change.
  • Msg kinds are snake_case verbs (toggle_rule, pick_folder); model fields are camelCase nouns.
  • Derived state is a helper, never a field. If markup needs it, export a single-Model function.

Comments policy

Read the full file on GitHub · 141 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. 2mo ago First seen · 141 lines · 1,481 tokens per session scan A 693347c40974

Subscribe to this mod's changes

spotless AGENTS.md is an instructions file published in the GitHub repository ripgrim/spotless (11 stars, last pushed 2mo ago), licensed MIT. It adds 1,481 tokens to every session, about $0.0059 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

spotless AGENTS.md compared with instructions from other repositories

spotless AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
spotless AGENTS.mdripgrim/spotlessInstructions file112mo agoMITA1,481Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA1,907GitHub Copilot