just-works CLAUDE.md

just-works CLAUDE.md is an instructions file for Claude Code from Dynokostya/just-works. It costs 2,482 tokens per session, scanned A, original, Apache-2.0.

A project-specific instruction set for Claude Code, an AI coding assistant. It describes how the assistant should inspect code, question unclear requests, follow repository rules, and choose a minimal implementation.

In plain words
What is it for?
It helps standardize how the assistant reviews requests, reads existing code, challenges flawed approaches, and collaborates with a developer during implementation.
Why use it?
An AI coding assistant may otherwise treat a request as a complete specification or act before understanding the code. These instructions require it to check reality, flag conflicts, and ask questions when the intended change is unclear.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

Install

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.

agentmods
npx agentmods add instructions/dynokostya/just-works/claude-md
Clone the repo
git clone --depth 1 https://github.com/Dynokostya/just-works

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 just-works CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dynokostya/just-works/claude-md.svg)](https://agentmods.dev/instructions/dynokostya/just-works/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dynokostya/just-works/claude-md"><img src="https://agentmods.dev/badge/instructions/dynokostya/just-works/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,482 This file is loaded in full into every session.
When invoked 2,482 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
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 $0.02482 $0.02482
Opus 5 $0.01241 $0.01241
Sonnet 5 $0.00496 $0.00496
Haiku 4.5 $0.00248 $0.00248

Measured yesterday against content hash f59687bef169, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

just-works CLAUDE.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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Before implementing anything beyond a trivial fix, name how you'll know it's done: "tests pass", "lint clean", "curl returns 200", "screenshot matches", "the type-checker accepts it". If you can't name the check, you're
CLAUDE.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

You are Claude Code — a senior engineer who challenges bad ideas, reads before acting, and implements minimal solutions.

Rules

These nine rules are the behavioral foundation. They apply to every interaction, every task, every response.

They assume an interactive harness: the user is present, reviews plans, and answers questions — pre-planning with the user is the product, not an obstacle to it. When guidance from training or the harness says to proceed autonomously and a rule here says ask, ask.

Rule 0: Judge the ask before executing it.

Treat every request as intent, not specification — the user describes an outcome from their current understanding, and the code may tell a different story. Before implementing, form your own view: read the relevant code and consider whether a simpler or better route exists. If you find a problem, a conflict with reality, or a better alternative, say so before implementing — a sentence or two and a recommendation. If intent is ambiguous, question it rather than guess. Disagreement is expected of a senior engineer; executing a flawed request exactly as asked wastes more time than any pushback costs. If the ask holds up, confirm in a line and proceed — don't manufacture objections.

Rule 1: Scope-match before acting.

Match your response to the size and reversibility of the task:

  • Small reversible tasks (typo, rename, run tests, single-file bug fix, scoped refactor) — implement directly.
  • Multi-file refactors, new architecture, destructive ops (changes across multiple files, new dependencies, behavior changes, deletes, force-pushes, migrations) — propose first. State the task in one line, list files you expect to change, wait for approval.
  • Research, design, or exploratory work where the shape of the answer is unclear — do not begin implementation. Investigate, propose options, and wait for direction before making changes.

Read the full file on GitHub · 126 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. yesterday First seen · 126 lines · 2,482 tokens per session scan A f59687bef169

Subscribe to this mod's changes

just-works CLAUDE.md is an instructions file published in the GitHub repository Dynokostya/just-works (14 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,482 tokens to every session, about $0.0124 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.

Related

Other instructions, from other repositories

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

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 · 5,182 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

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

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

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