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 instructions/ocean-industries-concept-lab/openbridge-webcomponents/argit clone --depth 1 https://github.com/Ocean-Industries-Concept-Lab/openbridge-webcomponentsWrote 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/ocean-industries-concept-lab/openbridge-webcomponents/ar)<a href="https://agentmods.dev/instructions/ocean-industries-concept-lab/openbridge-webcomponents/ar"><img src="https://agentmods.dev/badge/instructions/ocean-industries-concept-lab/openbridge-webcomponents/ar.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 | $0.01726 | $0.01726 |
| Opus 5 | $0.00863 | $0.00863 |
| Sonnet 5 | $0.00345 | $0.00345 |
| Haiku 4.5 | $0.00173 | $0.00173 |
Grade A, and why
openbridge-webcomponents ar.instructions.md 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AR / POI Overlay Components
The AR family renders points of interest over a live video or still image: markers that track detected objects, resolve their own overlaps, and expand into cards on interaction.
Every component here carries full class JSDoc, and Storybook autodocs surfaces it. This file covers what no single component's JSDoc can: how the pieces compose, and the traps that only show up across the family.
Layering
Five levels, outermost first. Each owns exactly one concern; pushing logic up or down the stack is the usual cause of bugs here.
<obc-poi-controller> geometry: maps detection coordinates onto the media
└─ media slot: <video> / <img>
└─ <obc-poi-layer-stack> selection across layers
└─ <obc-poi-layer> overlap resolution + layer height
├─ <obc-poi-data> a target
└─ <obc-poi-group> a cluster of targets
obc-poi-controller— the only component that knows about the media. It observes the slotted<video>/<img>, tracks natural vs rendered size, and appliesfit(contain|cover) so marker coordinates land on the right pixels. It also filtersdetectionsbyconfidenceMinandclassFilter, and drivesframeIndexfor frame-by-frame playback. Nothing below it should read media dimensions.obc-poi-layer-stack— coordinates selection across sibling layers viaselection-mode, emittinglayer-selection-changed.obc-poi-layer— resolves overlaps and reports its computed height. This is where most layout behaviour lives.obc-poi-group— one cluster: collapsed trigger ↔ expanded spread.obc-poi-data/-vessel/-aton— individual targets.
Overlap resolution: two strategies, not one
obc-poi-layer's overlapMode picks between two genuinely different algorithms,
each with its own helper module. They do not share state, and a change to one
does not affect the other:
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 · 134 lines · 1,726 tokens per session scan A 6802eb0f20d1
openbridge-webcomponents ar.instructions.md is an instructions file published in the GitHub repository Ocean-Industries-Concept-Lab/openbridge-webcomponents (91 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,726 tokens to every session, about $0.0086 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 2026-08-30.
Other instructions, from other repositories
fundamental-ngx AGENTS.md
AGENTS.md instructions for SAP/fundamental-ngx, covering angular 22+ development guidelines, persona, quick reference, essential commands and build/lint/test specific library.
primitives CLAUDE.md
Claude Code instructions for radix-ng/primitives, covering radix ng primitives — claude guide, project knowledge, project overview, monorepo structure and naming conventions.
wonder-blocks CLAUDE.md
Claude Code instructions for Khan/wonder-blocks, covering wonder blocks design system, technology stack, coding conventions, file & export naming and typescript.
melta-ui AGENTS.md
Instructions for tsubotax/melta-ui, covering melta ui — ai エージェント作業ガイド, アーキテクチャ概要, 最初に読むファイル, 読み込みモード and 作業ルール.
primitives AGENTS.md
AGENTS.md instructions for radix-ng/primitives, covering agent guide and storybook styling.
brandkit-mcp CLAUDE.md
Instructions for ejwhite7/brandkit-mcp, covering claude.md -- brandkit mcp, project overview, key concepts, repository structure and brand atomic system layout.