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.
curl -O https://raw.githubusercontent.com/jstxn/rein/main/.codex/skills/rein-review/SKILL.mdgit clone --depth 1 https://github.com/jstxn/reinWrote 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.
[](https://agentmods.dev/skills/jstxn/rein/rein-review)<a href="https://agentmods.dev/skills/jstxn/rein/rein-review"><img src="https://agentmods.dev/badge/skills/jstxn/rein/rein-review/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.
<a href="https://agentmods.dev/skills/jstxn/rein/rein-review"><img src="https://agentmods.dev/badge/skills/jstxn/rein/rein-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00027 | $0.00486 |
| Opus 5 | $0.00014 | $0.00243 |
| Sonnet 5 | $0.00005 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
rein-review 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rein-review
Use this after implementation and before committing to review your own diff for problems that verification commands alone will not catch.
Treat every changed line as needing a clear path back to the user's request or to cleanup made necessary by your own change.
When To Use
- Before any commit that touches more than a trivial change
- After a multi-file implementation pass
- When you are about to declare work complete
When Not To Use
- The change is a single-line typo fix with no surrounding edits
- rein-verify has already been run and covers diff review (avoid duplication)
Steps
- Read the full diff (staged and unstaged).
- For every changed file, verify you read it before editing it.
- Check for unrelated changes:
- files modified that are not part of the task
- adjacent code or comments touched without task need
- formatting-only changes in files you did not need to touch
- import reordering or whitespace changes outside the task scope
- Check for debug leftovers:
- console.log, print, debugger statements
- commented-out code that should be removed
- TODO/FIXME comments added without justification
- Check for test and fixture integrity:
- tests removed or weakened without explanation
- assertions loosened (exact match to contains, strict to loose)
- test data changed to make failures disappear
- new tests that only assert the happy path
- Check for scope drift:
- refactors beyond what the task required
- speculative cleanup beyond the request
- new abstractions or helpers for one-time use
- feature additions not in the original scope
- Apply the boundary rule:
- only clean up the mess created by this task unless the user explicitly asked for broader cleanup
- If any issue is found, fix it before committing.
- If all checks pass, state what was reviewed and confirm the diff is clean.
Output
Emit a short review note with:
- files reviewed
- issues found (if any) and how they were resolved
- confirmation that the diff is limited to the task scope
- any caveats or remaining concerns
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.
- 12d ago First seen · 59 lines · 27 tokens per session scan A 71af8876258e
rein-review is a skill published in the GitHub repository jstxn/rein (12 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 486 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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…