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.
curl -O https://raw.githubusercontent.com/open-horizon-labs/repo-native-alignment/main/.claude/agents/oh-aim.mdgit 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-aim)<a href="https://agentmods.dev/agents/open-horizon-labs/repo-native-alignment/oh-aim"><img src="https://agentmods.dev/badge/agents/open-horizon-labs/repo-native-alignment/oh-aim/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-aim"><img src="https://agentmods.dev/badge/agents/open-horizon-labs/repo-native-alignment/oh-aim.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 | $0.00022 | $0.02175 |
| Opus 5.5 | $0.00009 | $0.00870 |
| Sonnet 5.5 | $0.00004 | $0.00435 |
| Haiku 4.5 | $0.00002 | $0.00217 |
Grade A, and why
oh-aim 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 2mo 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 — 287 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
- Submit your full analysis as your final output — the caller will persist it to the session file
If no session file is referenced, produce your full output as text for the caller to handle.
/aim
Clarify the outcome you want. An aim is a change in user behavior, not a feature shipped. This is the first step in the Intent-Execution-Review loop.
The aim IS the abstraction. When you clarify what behavior you want to change, you're abstracting the business domain itself. Features are just the mechanism; the aim is why they matter.
When to Use
Invoke /aim when:
- Starting new work - Before diving into problem-statement or problem-space
- Scope feels fuzzy - You can describe what you're building but not why
- Multiple solutions seem valid - Aim clarifies which one actually moves the needle
- Work has drifted - Return to aim to check if you're still on track
- Team is misaligned - Shared aim surfaces hidden assumptions
Do not use when: You already have a crisp aim and need to explore the problem space or solution space. Move to /problem-statement or /problem-space instead.
The Aim Process
Step 1: State the Desired Behavior Change
Start with the user, not the system. What do you want users to do differently after this work ships?
"Users will [specific behavior] instead of [current behavior]."
Bad: "Add dark mode toggle" Good: "Users can work comfortably at night without eye strain"
Bad: "Improve onboarding flow" Good: "New users reach their first value moment within 5 minutes"
Key distinction: Features are outputs. Behavior changes are outcomes.
Step 2: Identify the Mechanism
The mechanism is your hypothesis - the causal lever you believe will produce the behavior change. It's the "because" that connects your work to the outcome.
"This will happen because [mechanism]."
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.
- 2mo ago First seen · 287 lines · 22 tokens per session scan A 048557996b31
oh-aim is an agent published in the GitHub repository open-horizon-labs/repo-native-alignment (6 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 2,175 once invoked, about $0.0001 per session on Opus 5.5. 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
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.