repo-native-alignment: Agent for Claude Code

.claude/agents/oh-execute.md

oh-execute is an agent for Claude Code from open-horizon-labs/repo-native-alignment. It costs 20 tokens per session (2,363 once invoked), scanned A, original, MIT.

A guided execution step for carrying out a chosen software solution. It covers preparation, building, checking whether the work still matches the intended outcome, and recovering when something goes wrong.

In plain words
What is it for?
Use it when the aim, solution, context, and constraints are already understood and it is time to build. Do not use it as the first step when the problem or approach is still unclear.
Why use it?
It gives implementation a defined point of departure after the goal and approach are clear. The alignment checks help catch work that has drifted away from the original plan.

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/oh-execute.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 oh-execute

README.md
[![agentmods](https://agentmods.dev/badge/agents/open-horizon-labs/repo-native-alignment/oh-execute.svg)](https://agentmods.dev/agents/open-horizon-labs/repo-native-alignment/oh-execute)
Your own site
<a href="https://agentmods.dev/agents/open-horizon-labs/repo-native-alignment/oh-execute"><img src="https://agentmods.dev/badge/agents/open-horizon-labs/repo-native-alignment/oh-execute.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,363 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 $0.00020 $0.02363
Opus 5 $0.00010 $0.01182
Sonnet 5 $0.00004 $0.00473
Haiku 4.5 $0.00002 $0.00236

Measured 7d ago against content hash b4a0b484cd2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

oh-execute 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/oh-execute.md · 336 lines

How it starts

The opening of the file, as written. The whole thing — 336 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:

  1. Read the session file to understand prior phase outputs
  2. After completing your analysis, update your section (## ) in the session file
  3. 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.

/execute

Do the actual work. Execute is the bridge from Solution Space to shipped code. Pre-flight checks, build, detect drift, salvage if needed.

Execute sits within the larger Intent -> Execution -> Review loop. This skill handles the Execution phase, which itself contains an inner loop: build, check alignment, course-correct or salvage.

When to Use

Invoke /execute when:

  • Aim is clear - you know the outcome you're trying to achieve
  • Solution is chosen - you've explored options and picked an approach
  • Context is loaded - you understand the constraints and guardrails
  • Ready to build - not still exploring or discovering

Do not use when:

  • Aim is unclear - use /aim first
  • Still exploring options - use /solution-space first
  • Problem is ambiguous - use /problem-space or /problem-statement first

The Execute Process

Step 1: Pre-flight Check

Before writing code, verify alignment:

Pre-flight Checklist:
[ ] Aim is clear - what outcome am I producing?
[ ] Constraints known - what must I NOT break?
[ ] Context loaded - do I have the codebase understanding I need?
[ ] Scope bounded - what am I specifically doing (and NOT doing)?
[ ] Success criteria - how will I know when I'm done?

If any box can't be checked, stop and address it before proceeding. Ask clarifying questions if requirements are ambiguous.

"The task is [task]. The aim is [aim]. I'm specifically doing [scope]. I will NOT be touching [out of scope]. Success looks like [criteria]."

Step 2: Build

Do the work. Keep it focused.

Build principles:

  • Work in small, testable increments
  • Commit logical units of change
  • Stay within the declared scope
  • If scope expands, pause and reassess (see Drift Detection)

Read the full file on GitHub · 336 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 · 336 lines · 20 tokens per session scan A b4a0b484cd2c

Subscribe to this mod's changes

oh-execute is an agent published in the GitHub repository open-horizon-labs/repo-native-alignment (4 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 2,363 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