rein-go

rein-go is a cursor rule for Cursor from jstxn/rein. It costs 20 tokens per session (1,109 once invoked), scanned A, original, MIT.

An end-to-end workflow for taking a coding task from clarification through planning, implementation, cleanup, review, and verification.

In plain words
What is it for?
Use it for broad tasks that need several stages. It can connect clarified requirements to a plan and then to implementation and checks.
Why use it?
It removes the need to coordinate each stage manually and keeps the work moving while stopping on failures, missing access, or dangerous actions.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: $skill-name invocation.

Good fit Use it for broad tasks that need several stages. It can connect clarified requirements to a plan and then to implementation and checks.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/jstxn/rein/rein-go
View source ↗ jstxn/rein
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.

Clone the repo
git clone --depth 1 https://github.com/jstxn/rein

Made for: Cursor.

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-go

README.md
[![agentmods](https://agentmods.dev/badge/rules/jstxn/rein/rein-go.svg)](https://agentmods.dev/rules/jstxn/rein/rein-go)
Your own site
<a href="https://agentmods.dev/rules/jstxn/rein/rein-go"><img src="https://agentmods.dev/badge/rules/jstxn/rein/rein-go.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,109 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 $0.00020 $0.01109
Opus 5 $0.00010 $0.00554
Sonnet 5 $0.00004 $0.00222
Haiku 4.5 $0.00002 $0.00111

Measured 8d ago against content hash 7d386cc517ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

rein-go 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.

.cursor/rules/rein-go.mdc · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

rein-go

Use this when the user wants one REIN-controlled flow instead of manually invoking rein-interview, rein-plan, implementation, cleanup, review, and verification as separate steps.

rein-go is the end-to-end orchestration surface for REIN.

When To Use

  • The user wants one continuous REIN workflow with minimal pauses
  • The task is broad enough to need clarification, planning, implementation, and post-implementation review
  • A completed rein-interview bundle already exists and should feed directly into planning and implementation
  • The user explicitly invokes $rein-go, /rein-go, or asks for a single flow command

When Not To Use

  • The task is already a tiny single-file change
  • The user explicitly wants only one stage, such as interview-only or plan-only work
  • The user wants to skip clarification and planning entirely

Flow Contract

  • Public entrypoint: rein go
  • Wrapper triggers: $rein-go and /rein-go
  • Default posture: keep going with minimal pauses once the flow starts
  • Hard stop on:
    • dangerous or destructive actions that require approval
    • missing permissions or blocked tool access
    • any failed stage: plan, implementation, cleanup, review, or verify
  • Preserve the current install and hook philosophy; do not turn REIN into a hook-first enforcement layer

Runtime Helper

Start the flow through the runtime:

rein go "<task>" --json

If a completed interview bundle already exists:

rein go --from-interview <slug|path> --json

Then use:

rein go status --slug <slug> --json
rein go resume --slug <slug> --json
rein go advance --slug <slug> --stage <stage> --status <completed|failed|blocked> ... --json

Treat the returned flow state as the source of truth for current stage, resume point, stop reason, and downstream stage artifacts.

Stage Order

  1. Interview
    • Bare rein go "<task>" initializes the flow and starts rein-interview automatically.
    • If the flow was started with --from-interview, the interview stage is marked completed from the bundle.
    • While interview is still active, use the normal rein interview ... runtime commands and present the user-facing interview exactly like rein-interview does, including the clarity score and question frame.
    • Never answer interview rounds on the user's behalf, never auto-crystallize, and never skip directly to planning in fresh mode.
    • If rein go resume --slug <slug> --json still returns currentStage: interview and recommends rein interview crystallize ..., the interview is not done yet; crystallize first, then resume again to advance into planning.

Read the full file on GitHub · 121 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. 8d ago First seen · 121 lines · 20 tokens per session scan A 7d386cc517ff

Subscribe to this mod's changes

rein-go is a cursor rule published in the GitHub repository jstxn/rein (12 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 1,109 once invoked, about $0.0001 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.