repo-native-alignment: Agent for Claude Code

.claude/agents/ship.md

ship is an agent for Claude Code from open-horizon-labs/repo-native-alignment. It costs 25 tokens per session (5,161 once invoked), scanned A, original, MIT.

A release workflow that takes implemented code through checks, review, and delivery to a merge request. RNA here refers to the project’s repository-alignment tools, which provide project context and code navigation.

In plain words
What is it for?
Use it to inspect project context, verify implementation alignment, run the project’s delivery checks, review the final diff, and prepare work for merging. The exact pipeline depends on the project’s RNA setup.
Why use it?
It puts quality checks and final review around the path from code changes to a proposed merge. It also checks whether changes remain aligned with the project and asks for an independent final-diff approval.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents; mentions AGENTS.md.

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/ship.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 ship

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/open-horizon-labs/repo-native-alignment/ship"><img src="https://agentmods.dev/badge/agents/open-horizon-labs/repo-native-alignment/ship.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 5,161 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 $0.05161
Opus 5 $0.00013 $0.02580
Sonnet 5 $0.00005 $0.01032
Haiku 4.5 $0.00003 $0.00516

Measured 9d ago against content hash 24a56bb9dfde, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ship 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 9d 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/ship.md · 447 lines

How it starts

The opening of the file, as written. The whole thing — 447 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RNA /ship Pipeline

The full quality gate for this project. Run sequentially — each step must complete before the next begins. Do not wait for user prompts between steps. When one step completes, immediately start the next.

You are an RNA power user. Before every Grep or Read for code understanding, ask: "Is there an RNA tool for this?"

Two RNA access paths — use the right one:

  • MCP tools (search, repo_map, outcome_progress, list_roots) — use for project-level context: guardrails, outcomes, metis, impact analysis. These query the main RNA repo index.
    • Worktree-aware queries: use the repo parameter to scope to your worktree's graph:
      mcp__rna-mcp__search(query="handle_search", repo="/path/to/worktree")
      mcp__rna-mcp__repo_map(repo="/path/to/worktree")
      
      Requires the worktree to be scanned: repo-native-alignment scan --repo /path/to/worktree
  • CLI in your worktree (repo-native-alignment search --repo . "query", repo-native-alignment graph --node "..." --repo . --mode neighbors) — use for code navigation WITHIN your working directory. Always pass --repo . so it reads your local worktree's index.

Every Grep/Read you use instead of an RNA tool is a friction event — log it with severity skipped to .oh/friction-logs/. When an RNA tool fails, log that too. A ship run with 0 friction events and 20 Grep calls isn't frictionless — it's unmonitored.

MANDATORY scan before any code navigation: The worktree index must be live before you read any source file. See the scan gate in Pre-flight step 6 below.

CARGO BUILD GUARDRAIL: Never run two cargo builds against the same target/ directory. Before building, sanity-check you're not duplicating: ps aux | grep cargo | grep -v grep. A second cargo process targeting the same directory blocks silently on the file lock. See .oh/guardrails/no-parallel-cargo-agents.md.

Arguments

/ship <PR-number> — run the pipeline against a specific PR.

Read the full file on GitHub · 447 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. 9d ago First seen · 447 lines · 25 tokens per session scan A 24a56bb9dfde

Subscribe to this mod's changes

ship is an agent published in the GitHub repository open-horizon-labs/repo-native-alignment (5 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 5,161 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

deployment-specialist

Handles all deployment operations.

luongnv89/claude-howto · 8 tokens

geo-roadmap-release-manager

Manages SemVer decisions, package version bump proposals, roadmap alignment, release readiness, tag checklist, CI gate review, and post-merge release sequencing for GEO Optimizer and GeoReady.

Auriti-Labs/geo-optimizer-skill · 44 tokens

release-validator

Validates release readiness by checking tests, build, dependencies, and changelog. Use before creating a release.

rlajous/claude-code-commands · 25 tokens

pr-ghostwriter

Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.

komunite/kalfa · 81 tokens

iris

GitHub operations specialist — branches, pull requests, issues, releases, tags. Called by zeus after review. Never pushes or merges without explicit human approval. Integrates with VS Code GitHub Pull Requests extension.

ils15/pantheon-legacy · 45 tokens

shipper

Deployment pipeline agent that executes the full ship sequence: pre-ship checks, conventional commit, feature branch + PR, CI verification, and rollback documentation. Use in Phase 5 after Gate 2 passes. Never commits directly to main. Not for implementation or review approval.

ngocsangyem/MeowKit · 57 tokens