Borrowing it
Nothing to install: this file belongs to peters/horizon. 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/peters/horizon/main/AGENTS.mdgit clone --depth 1 https://github.com/peters/horizonWrote 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/peters/horizon/agents-md)<a href="https://agentmods.dev/instructions/peters/horizon/agents-md"><img src="https://agentmods.dev/badge/instructions/peters/horizon/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/peters/horizon/agents-md"><img src="https://agentmods.dev/badge/instructions/peters/horizon/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 | $0.13764 | $0.13764 |
| Opus 5.5 | $0.05506 | $0.05506 |
| Sonnet 5.5 | $0.02753 | $0.02753 |
| Haiku 4.5 | $0.01376 | $0.01376 |
Grade D, and why
horizon AGENTS.md scanned grade D with 3 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 2d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Debian/Ubuntu: `sudo apt install -y build-essential pkg-config libxkbcommon-dev libwayland-dev libxcb-render0-dev libxcb-shape0-dev libxcb-xfixes0-dev libvulkan-dev libgl-dev cmake nasm` Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/peters/localci/main/install.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/peters/localci/main/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 584 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Horizon — Agent Guidelines
Self-review and PR review
- The implementing agent reviews the complete diff once, fixes its findings, and runs the applicable checks before the first push.
- After that, rely on the upstream repository's automatic PR review. Address its feedback and validate the affected changes without another full self-review round.
- Never assign, request, or re-request Copilot, Claude, or another automated reviewer. Do not use reviewer assignments, labels, comments, CLI commands, APIs, workflow dispatches, or PR state changes to trigger a review. The upstream repository manages automatic review.
- Do not start a separate local review agent or a CLI review loop. This rule also applies to external contributions and overrides review loops in skills or linked procedures.
- Keep CI, applicable smoke checks, feedback handling, and merge authorization. Check which commit a review covers; do not claim that an earlier review covers later changes. If a required automatic review is missing or fails, report the blocker without requesting another review.
- Keep
CLAUDE.mdas the single import@AGENTS.md. Put repository instructions inAGENTS.md.
Source of truth for all contributors and AI agents working on this project.
Company and products
horizon is not a Finter Mobility repository, but it runs the agents, browser panels and device panels that all of them use, so it must know which repos need each other. The shared map lives in the private fintermobilityas/company repo, checked out as ~/github/company; treat docs/products.json there as the source when deciding which companion repos to open, check or brief together:
- What every repo does and how they connect:
../company/docs/products.md(machine-readable:../company/docs/products.json). - This repo's page:
../company/docs/products/horizon.md. - Shared maintenance rules (Dependabot, .NET, MongoDB, PRs, native packages, rollout order):
../company/AGENTS.md. - Companion lookups: for a repo X, its companions are the
edgesinproducts.jsonwherefromortois X;check_together: truemeans a change to that contract must be verified in both repos (format:docs/products.schema.json,schema_version1).
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.
- 2d ago Changed · +1 lines · +150 tokens per session be3c7d53b1d3
- 3d ago Changed · -32 lines · -840 tokens per session 6377bc71a719
- 4d ago Changed · +56 tokens per session 2d58173611ef
- 5d ago Changed · -24 lines · -522 tokens per session 4338e8b1839d
- 6d ago Changed · +44 tokens per session b1bac1cfd869
- 10d ago Changed · -22 lines · -391 tokens per session 86a2a2bd4c69
- 12d ago Changed · +1 lines · +161 tokens per session 87f2979c70e8
- 14d ago Changed · +8 lines · +455 tokens per session fc95a71ac61c
- 15d ago Changed · +54 lines · +1,340 tokens per session 59eed8b7186b
- 16d ago First seen · 598 lines · 13,311 tokens per session scan D b1c4d9ff21d9
horizon AGENTS.md is an instructions file published in the GitHub repository peters/horizon (722 stars, last pushed today), licensed MIT. It adds 13,764 tokens to every session, about $0.0551 per session on Opus 5.5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.