rein: Command for Claude Code

.claude/commands/rein-retro.md

rein-retro is a command for Claude Code from jstxn/rein. It costs 25 tokens per session (157 once invoked), scanned A, original, MIT.

A short post-mortem workflow for examining a missed requirement, failed check, regression, or suspicious shortcut. It records the failure, its cause, the missing evidence, and a rule to improve the process.

In plain words
What is it for?
Use it after a failed verification, regression, incomplete search, unsupported claim, or reward-hacking shortcut. It is for documenting what happened and what the harness or workflow should change.
Why use it?
It turns mistakes into specific changes to the working process instead of leaving their causes unclear. This helps prevent the same kind of miss from happening again.

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-retro.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-retro

README.md
[![agentmods](https://agentmods.dev/badge/commands/jstxn/rein/rein-retro/github.svg)](https://agentmods.dev/commands/jstxn/rein/rein-retro)
Your own site
<a href="https://agentmods.dev/commands/jstxn/rein/rein-retro"><img src="https://agentmods.dev/badge/commands/jstxn/rein/rein-retro/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 rein-retro

Your own site · 80×15
<a href="https://agentmods.dev/commands/jstxn/rein/rein-retro"><img src="https://agentmods.dev/badge/commands/jstxn/rein/rein-retro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 157 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 $0.00025 $0.00157
Opus 5 $0.00013 $0.00078
Sonnet 5 $0.00005 $0.00031
Haiku 4.5 $0.00003 $0.00016

Measured 10d ago against content hash 009388d59f1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

rein-retro 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 10d 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-retro.md · 32 lines

What it actually says

rein-retro

Use this after a miss, failed check, or suspicious shortcut.

Steps

  1. State what failed.
  2. Identify the false assumption or missed search step.
  3. Classify the miss:
    • bluffing
    • incomplete search
    • insufficient verification
    • reward hacking
    • other
  4. State what evidence would have prevented the miss.
  5. Propose one concrete protocol improvement.

Output

Emit a short retro note with:

  • failure
  • root assumption
  • miss classification
  • missing evidence
  • rule or prompt update to add back into the harness
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. 10d ago First seen · 32 lines · 25 tokens per session scan A 009388d59f1d

Subscribe to this mod's changes

rein-retro is a command published in the GitHub repository jstxn/rein (12 stars, last pushed 4mo ago), licensed MIT. It adds 25 tokens to every session and 157 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.