repo-native-alignment: Skill for Claude Code

.agents/skills/review/SKILL.md

review is a skill for Claude Code, Codex from open-horizon-labs/repo-native-alignment. It costs 35 tokens per session (2,939 once invoked), scanned A, original, MIT.

A second-opinion check of code changes against the original goal before committing or opening a pull request.

In plain words
What is it for?
Use it at natural pause points, before commits or pull requests, or when the implementation no longer feels aligned with the task.
Why use it?
It helps catch scope growth, missed requirements, and unintended drift while changes are still easy to adjust.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents).

This is open-horizon-labs/repo-native-alignment's own configuration. It tells Claude Code and Codex how to work on repo-native-alignment 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 repo-native-alignment configures →

Reuse

Borrowing it

Nothing to install: this file belongs to open-horizon-labs/repo-native-alignment. 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/open-horizon-labs/repo-native-alignment/main/.agents/skills/review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/open-horizon-labs/repo-native-alignment

Made for: Claude Code, Codex.

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 review

README.md
[![agentmods](https://agentmods.dev/badge/skills/open-horizon-labs/repo-native-alignment/review/github.svg)](https://agentmods.dev/skills/open-horizon-labs/repo-native-alignment/review)
Your own site
<a href="https://agentmods.dev/skills/open-horizon-labs/repo-native-alignment/review"><img src="https://agentmods.dev/badge/skills/open-horizon-labs/repo-native-alignment/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.

agentmods 80×15 button for review

Your own site · 80×15
<a href="https://agentmods.dev/skills/open-horizon-labs/repo-native-alignment/review"><img src="https://agentmods.dev/badge/skills/open-horizon-labs/repo-native-alignment/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,939 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 $0.00035 $0.02939
Opus 5 $0.00017 $0.01470
Sonnet 5 $0.00007 $0.00588
Haiku 4.5 $0.00003 $0.00294

Measured 12d ago against content hash e04b1d89471b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

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.

.agents/skills/review/SKILL.md · 407 lines

How it starts

The opening of the file, as written. The whole thing — 407 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/review

A second opinion before committing. Review checks alignment between intent and execution, detects drift, and decides: continue, adjust, or salvage.

This is part of the Intent > Execution > Review loop that runs at every scale--from a single commit to a multi-week project. Review closes the loop.

The same skill also provides an independent review mode for /ship. A fresh, separate sub-agent returns an explicit APPROVE or REQUEST CHANGES; when invoked for the final-diff gate, it reviews the exact commit proposed for merge.

When to Use

Invoke /review when:

  • Before committing - natural checkpoint before code hits the branch
  • At natural pause points - end of a work session, end of a subtask
  • Something feels off - you've been coding a while and lost track of where you are
  • Scope seems to have grown - the task feels bigger than when you started
  • Before PRs - final check before requesting review from humans

Do not use when: You're in deep flow and making progress. Don't interrupt productive work. Review at natural breaks, not arbitrary intervals.

Independent Review Mode

Use this mode only when invoked by /ship as a fresh, separate reviewer sub-agent. Step 2 uses it for early adversarial feedback; step 10c invokes a different fresh reviewer for the binding final-diff gate.

Isolation contract

  • The reviewer must be a distinct sub-agent, not the implementer and not a reused earlier reviewer.
  • Start with fresh context.
  • Inputs are limited to:
    • the exact final diff and reviewed commit SHA;
    • the linked issue acceptance criteria;
    • relevant guardrails and metis;
    • RNA graph impact for the changed areas.
  • Do not read or request the implementation session, implementation reasoning, prior conversation, or a summary defending the chosen solution.

Review contract

  1. Verify every acceptance criterion against the diff.
  2. Check relevant hard and soft guardrails.
  3. Check changed-area impact and likely regressions using the provided RNA context.
  4. Identify concrete correctness, security, maintainability, testing, delivery, and policy-consistency findings.
  5. Return exactly one binding verdict:
    • APPROVE — no unresolved actionable findings.
    • REQUEST CHANGES — one or more actionable findings must be fixed.

Read the full file on GitHub · 407 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. 12d ago First seen · 407 lines · 35 tokens per session scan A e04b1d89471b

Subscribe to this mod's changes

review is a skill published in the GitHub repository open-horizon-labs/repo-native-alignment (5 stars, last pushed 3d ago), licensed MIT. It adds 35 tokens to every session and 2,939 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 2026-08-31.