repo-native-alignment: Agent for Claude Code

.claude/agents/oh-problem-space.md

oh-problem-space is an agent for Claude Code from open-horizon-labs/repo-native-alignment. It costs 17 tokens per session (2,379 once invoked), scanned A, a copy of style-reviewer, MIT.

A problem-exploration agent that maps what a project is trying to improve and which constraints shape the solution.

In plain words
What is it for?
Use it when starting work, facing repeated blockers, accumulating patches, or questioning whether current constraints are actually necessary.
Why use it?
It helps prevent coding the wrong solution before the problem, priorities, and assumptions are understood.

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-problem-space.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-problem-space

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/open-horizon-labs/repo-native-alignment/oh-problem-space"><img src="https://agentmods.dev/badge/agents/open-horizon-labs/repo-native-alignment/oh-problem-space.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,379 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 86% copy Near-identical to another mod 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 $0.00017 $0.02379
Opus 5 $0.00009 $0.01189
Sonnet 5 $0.00003 $0.00476
Haiku 4.5 $0.00002 $0.00238

Measured 9d ago against content hash b923140bd2f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

oh-problem-space 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.

Origin

This is a copy

86% identical to style-reviewer — 332 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/oh-problem-space.md · 295 lines

How it starts

The opening of the file, as written. The whole thing — 295 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.

/problem-space

Map the terrain where solutions live. What are we optimizing? What constraints do we treat as real? Which constraints can be questioned?

Problem space exploration precedes solution space. Understanding the terrain is the work. Jump to code too early and you'll build the wrong thing fast.

When to Use

Invoke /problem-space when:

  • Starting new work - Before jumping to implementation, understand what you're actually solving
  • Hitting repeated blockers - The same problems keep appearing in different forms
  • Patches accumulating - Third config flag for the same bug signals you're treating symptoms
  • Estimates feel off - When time estimates are wrong by an order of magnitude, the problem isn't understood
  • Agent is talking itself out of constraints - "For this prototype we don't have time" when the constraint matters

Do not use when: The problem is well-understood and you're already in execution. Problem space is for grounding, not for stalling.

The Problem Space Process

Step 1: State the Objective Function

What are we actually optimizing? Not the feature, the outcome.

"We are optimizing for [outcome]."

Be precise. "Build a login page" is a feature. "Reduce time-to-first-value for new users" is an objective. The aim IS the abstraction.

Ask:

  • What change in behavior would indicate success?
  • What metric would move if this worked?
  • What problem disappears if we get this right?

Step 2: Map the Constraints

List what we're treating as fixed. Be explicit about each constraint's nature:

Constraint: [the boundary]
Type: [hard | soft | assumed]
Reason: [why it exists]
Questioning: [could this be false?]

Read the full file on GitHub · 295 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 · 295 lines · 17 tokens per session scan A b923140bd2f8

Subscribe to this mod's changes

oh-problem-space is an agent published in the GitHub repository open-horizon-labs/repo-native-alignment (5 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 2,379 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to style-reviewer, differing in 332 lines, and is treated as a copy.