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.
npx agentmods add agents/open-horizon-labs/repo-native-alignment/oh-problem-statementgit 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-problem-statement)<a href="https://agentmods.dev/agents/open-horizon-labs/repo-native-alignment/oh-problem-statement"><img src="https://agentmods.dev/badge/agents/open-horizon-labs/repo-native-alignment/oh-problem-statement.svg" alt="Measured on agentmods" 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 | $0.02467 |
| Opus 5 | $0.00011 | $0.01234 |
| Sonnet 5 | $0.00004 | $0.00493 |
| Haiku 4.5 | $0.00002 | $0.00247 |
Grade A, and why
oh-problem-statement 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 5d 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 — 301 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.
/problem-statement
Define the framing. Change the statement, change the solution space.
A problem statement is not the problem itself—it's the lens through which you see the problem. Different framings open different solution spaces. The right framing makes good solutions obvious; the wrong framing makes them invisible.
When to Use
Invoke /problem-statement when:
- Starting new work - Before diving into solutions, articulate what you're actually solving
- Solutions feel off - When proposed solutions seem convoluted or like workarounds
- Oscillating on approach - When you keep changing direction, the framing might be wrong
- Suspected X-Y problem - When someone asks for a specific solution but the underlying need is unclear
- Requirements keep expanding - Scope creep often signals a framing mismatch
- After
/aimbut before/solution-space- The natural sequence: aim defines outcome, problem statement frames the challenge
Do not use when: You already have a crisp problem statement and are ready to explore solutions. Move to /solution-space.
The Framing Process
Step 1: Surface the Current Framing
Before reframing, understand how the problem is currently being seen:
"The problem is currently framed as: [how it's being described]"
Capture:
- What's the stated problem?
- What assumptions are embedded in how it's described?
- What's being treated as fixed vs. changeable?
Step 2: Detect X-Y Problems
Watch for the X-Y problem pattern: someone asks for Y (their attempted solution) when they actually need X (the real problem).
Signs of X-Y mismatch:
- Request is oddly specific for what seems like a simple goal
- The solution feels like a workaround
- "How do I do [technique]?" without explaining why
- Convoluted multi-step approach to something that should be simple
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.
- 5d ago First seen · 301 lines · 22 tokens per session scan A 86b1df31c126
oh-problem-statement is an agent published in the GitHub repository open-horizon-labs/repo-native-alignment (4 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 2,467 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
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.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.