Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/open-horizon-labs/repo-native-alignmentWrote 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/agents/open-horizon-labs/repo-native-alignment/oh-ship)<a href="https://agentmods.dev/agents/open-horizon-labs/repo-native-alignment/oh-ship"><img src="https://agentmods.dev/badge/agents/open-horizon-labs/repo-native-alignment/oh-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.
<a href="https://agentmods.dev/agents/open-horizon-labs/repo-native-alignment/oh-ship"><img src="https://agentmods.dev/badge/agents/open-horizon-labs/repo-native-alignment/oh-ship.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 | $0.00019 | $0.02429 |
| Opus 5 | $0.00010 | $0.01215 |
| Sonnet 5 | $0.00004 | $0.00486 |
| Haiku 4.5 | $0.00002 | $0.00243 |
Grade A, and why
oh-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 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.
How it starts
The opening of the file, as written. The whole thing — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Context
If the assignment includes a session name or .oh/.md path:
- Read the session file to understand prior phase outputs
- After completing your analysis, update your section (## ) in the session file
- Submit a concise summary as your final output
If no session file is referenced, produce your full output as text for the caller to handle.
/ship
Optimize the delivery path from completed work to working install. The insight: when execution is cheap, delivery is the work.
Ship is the final step of the Execution phase. Code that isn't in users' hands isn't delivering value. This skill identifies and removes friction in your delivery path.
When to Use
Invoke /ship when:
- Execution is complete - code is ready, tests pass, review is done
- You need to deploy - getting changes from merged to running
- Delivery feels slow - the code is done but it's not reaching users
- You're blocked on gates - reviews, scans, approvals are piling up
- You want to automate delivery - make the path from code to install frictionless
Do not use when: You're still building. Ship is for getting completed work to users, not for execution.
The Ship Process
Step 1: Identify the Delivery Path
Before shipping, map the path from code to working install:
"The delivery path for this change is: [local] -> [PR/review] -> [merge] -> [CI/CD] -> [staging/prod] -> [user install]."
Be specific. Name each step and who/what owns it.
Step 2: Assess the Delivery-Path Tax
The delivery-path tax is the friction that slows velocity. Identify where time is lost:
Review Time
- How long do PRs wait for review?
- Is the review queue a bottleneck?
- Can AI review pre-check before human review?
Merge Time
- Are there merge conflicts blocking progress?
- Is the main branch unstable?
- How long from approval to merge?
Gate/Scan Time
- Security scans, compliance checks, quality gates
- Are gates running in parallel or serial?
- Which gates are flaky or slow?
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.
- 10d ago First seen · 328 lines · 19 tokens per session scan A 0b943d05dea5
oh-ship is an agent published in the GitHub repository open-horizon-labs/repo-native-alignment (5 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 2,429 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.