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/AGENTS.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/instructions/open-horizon-labs/repo-native-alignment/agents-md)<a href="https://agentmods.dev/instructions/open-horizon-labs/repo-native-alignment/agents-md"><img src="https://agentmods.dev/badge/instructions/open-horizon-labs/repo-native-alignment/agents-md/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/instructions/open-horizon-labs/repo-native-alignment/agents-md"><img src="https://agentmods.dev/badge/instructions/open-horizon-labs/repo-native-alignment/agents-md.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 | $0.03678 | $0.03678 |
| Opus 5 | $0.01839 | $0.01839 |
| Sonnet 5 | $0.00736 | $0.00736 |
| Haiku 4.5 | $0.00368 | $0.00368 |
Grade A, and why
repo-native-alignment AGENTS.md scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **test-with-real-mcp-client**: Test MCP changes with real clients, not just curl. [Details](.oh/guardrails/test-with-real-mcp-client.md) How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open Horizons Framework
The shift: Action is cheap. Knowing what to do is scarce. We don't build features, we build capabilities.
The sequence: aim → problem-space → problem-statement → solution-space → draft PR → execute → ship
Repo-local skills: The canonical workflow skills for this project live in .agents/skills/. Agents must prefer these repo-local versions over similarly named global skills so the workflow travels with the repository.
Where to start (triggers):
- Can't explain why you're building this →
/aim - Keep hitting the same blockers →
/problem-space - Solutions feel forced →
/problem-statement - About to start coding →
/solution-space - Work is drifting or reversing →
/salvage
Reflection skills (use anytime):
/review- Check alignment before committing/dissent- Seek contrary evidence before one-way doors/salvage- Extract learning, restart clean
Draft PR (between solution-space and execute)
After /solution-space produces a recommendation, create a draft PR before writing code. The draft PR:
- Names the branch, states the problem, and links the issue
- Summarizes the chosen solution from solution-space analysis
- Becomes the home for all /ship pipeline comments (review, dissent, adversarial test, merit assessment, etc.)
/executewrites code on this branch;/shipruns the quality gate on this PR
This ensures every piece of work has a PR home before implementation begins. No orphan branches, no post-hoc PR creation.
/ship Definition (for this project)
/ship = the full quality gate before merge, defined in .claude/agents/ship.md.
Summary: review → dissent → fix → mark ready → adversarial test → merit → resolve TODOs → manual verify → delivery verify → README → smoke+CI → final comment sweep → fresh final-diff approval → merge.
Step 3b (mark ready) converts the draft PR to ready-for-review, which triggers smoke tests gated behind draft == false so they skip during the draft phase when code is still being iterated on.
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.
- today Changed · +2 lines · +195 tokens per session ded78ab19f6c
- yesterday Changed · +1 lines · +47 tokens per session a2b4c5ea7e88
- 9d ago First seen · 176 lines · 3,436 tokens per session scan A 33d67cb83a81
repo-native-alignment AGENTS.md is an instructions file published in the GitHub repository open-horizon-labs/repo-native-alignment (5 stars, last pushed today), licensed MIT. It adds 3,678 tokens to every session, about $0.0184 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.