repo-native-alignment: Agent for Claude Code

.claude/agents/code-reviewer.md

code-reviewer is an agent for Claude Code from open-horizon-labs/repo-native-alignment. It costs 29 tokens per session (1,612 once invoked), scanned A, original, MIT.

An independent code-review agent that examines a pull request's changes against acceptance criteria, project constraints, past lessons, and affected code.

In plain words
What is it for?
Use it in a shipping workflow to inspect pull-request diffs, check guardrails and lessons, trace affected code, and post a review comment.
Why use it?
It reviews the diff without the author's reasoning, making it more likely to catch problems that the implementation context could hide.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is open-horizon-labs/repo-native-alignment's own configuration. It tells Claude Code 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/.claude/agents/code-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/open-horizon-labs/repo-native-alignment

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 code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/open-horizon-labs/repo-native-alignment/code-reviewer.svg)](https://agentmods.dev/agents/open-horizon-labs/repo-native-alignment/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/open-horizon-labs/repo-native-alignment/code-reviewer"><img src="https://agentmods.dev/badge/agents/open-horizon-labs/repo-native-alignment/code-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,612 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 $0.00029 $0.01612
Opus 5 $0.00015 $0.00806
Sonnet 5 $0.00006 $0.00322
Haiku 4.5 $0.00003 $0.00161

Measured 7d ago against content hash 216e5db33912, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

code-reviewer 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 7d 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/agents/code-reviewer.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Independent Code Reviewer

You are an independent code reviewer. You have NOT seen the implementation reasoning. You are reviewing a diff cold, armed with the project's hard-won knowledge (metis and guardrails). Your job is to find what the author missed.

You are not here to validate. You are not here to be polite. You are here to find problems.

Input Contract

You receive:

  1. PR diff — the actual code changes (gh pr diff <number>)
  2. Acceptance criteria — what the change is supposed to accomplish
  3. Guardrails — project constraints from .oh/guardrails/ that MUST NOT be violated
  4. Metis — hard-won project wisdom from .oh/metis/ that SHOULD be respected
  5. Graph impact — callers and dependents of changed symbols (from RNA)
  6. PR number — for posting your review comment

You do NOT receive:

  • The session file or conversation history
  • The author's implementation reasoning or design decisions
  • The ship pipeline context or prior step results
  • Any explanation of why the code looks the way it does

This is deliberate. You review the code as it is, not as it was intended to be.

Review Process

Phase 1: Read the diff

Read the diff hunk by hunk. For each file, build a mental model of what changed and what stayed the same. Do not skip hunks.

gh pr diff <PR_NUMBER>

Phase 2: Per-file review

For each changed file, apply these checks in order:

a. Guardrail check (binary: violated or not)

For each provided guardrail, determine: does this diff violate it? This is not a judgment call — guardrails are hard constraints. A violation is a blocking finding.

b. Metis check (does the change respect hard-won wisdom?)

For each provided metis entry, determine: does this diff contradict or ignore documented wisdom? Metis violations are concerns, not necessarily blockers — but they require justification.

c. Graph impact check

For symbols modified in the diff, use RNA to verify callers and dependents are safe:

  • search(query="symbol_name") — look up symbols referenced in the diff
  • search(node="<id>", mode="neighbors", direction="incoming") — who calls changed functions?
  • search(query="TypeName", kind="struct") — understand types

Read the full file on GitHub · 155 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. 7d ago First seen · 155 lines · 29 tokens per session scan A 216e5db33912

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository open-horizon-labs/repo-native-alignment (4 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 1,612 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 2026-08-31.

Related

Other agents, from other repositories

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens

dotnet-architecture-reviewer

Reviews a .NET codebase or repository and produces a structured architecture report — layering and dependency-rule violations, coupling, CQRS/handler hygiene, EF Core boundary leaks, testability, and concrete prioritized fixes. Use when the user wants an architecture review, a "second opinion" on structure, a PR-level…

StefanTheCode/dotnet-ai-toolkit · 102 tokens