rein: Command for Claude Code

.claude/commands/rein-scope.md

rein-scope is a command for Claude Code from jstxn/rein. It costs 31 tokens per session (339 once invoked), scanned A, original, MIT.

A scoping workflow for requests that are too large, contradictory, or unclear to complete safely in one pass. It creates an agreed boundary around the work and identifies missing information.

In plain words
What is it for?
It is for separating required work from optional work, defining exclusions, resolving conflicting requirements, and asking for the information needed to proceed.
Why use it?
It prevents unplanned expansion and makes trade-offs explicit before implementation begins.

Command for Claude Code

Written for Claude Code: installed under .claude/.

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

View source ↗ jstxn/rein
Reuse

Borrowing it

Nothing to install: this file belongs to jstxn/rein. 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/jstxn/rein/main/.claude/commands/rein-scope.md
Clone the repo
git clone --depth 1 https://github.com/jstxn/rein

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 rein-scope

README.md
[![agentmods](https://agentmods.dev/badge/commands/jstxn/rein/rein-scope.svg)](https://agentmods.dev/commands/jstxn/rein/rein-scope)
Your own site
<a href="https://agentmods.dev/commands/jstxn/rein/rein-scope"><img src="https://agentmods.dev/badge/commands/jstxn/rein/rein-scope.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 339 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00031 $0.00339
Opus 5 $0.00015 $0.00169
Sonnet 5 $0.00006 $0.00068
Haiku 4.5 $0.00003 $0.00034

Measured 8d ago against content hash 6544b5bf0814, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

rein-scope 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 8d 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/commands/rein-scope.md · 46 lines

What it actually says

rein-scope

Use this when the work as stated is too large for a single pass, contains contradictions, or needs explicit boundaries before implementation begins.

When To Use

  • The request implies more work than can be safely completed in one session
  • Requirements contradict each other or contradict existing behavior
  • The user asks for everything but constraints demand tradeoffs
  • Scope creep is likely without an explicit boundary

When Not To Use

  • The task is already well-scoped with clear acceptance criteria
  • Deep-interview has already produced a spec with explicit non-goals
  • The user explicitly asks to skip scoping

Steps

  1. Restate the full request as understood.
  2. Identify every distinct deliverable implied by the request.
  3. Classify each deliverable:
    • must: required for the work to be considered complete
    • should: valuable but deferrable without breaking the core intent
    • will not: explicitly out of scope for this pass
  4. For each contradiction or tension, state the conflict and propose a resolution with tradeoffs.
  5. Identify what information is missing to commit to the scope.
  6. Present the scope contract for user confirmation before proceeding.

Output

Emit a scope contract with:

  • restated request
  • must / should / will-not classification
  • conflicts identified and proposed resolutions
  • missing information
  • explicit confirmation request

Do not begin implementation until the user confirms the scope contract.

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. 8d ago First seen · 46 lines · 31 tokens per session scan A 6544b5bf0814

Subscribe to this mod's changes

rein-scope is a command published in the GitHub repository jstxn/rein (12 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 339 once invoked, about $0.0002 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.