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/ocean-industries-concept-lab/openbridge-webcomponents/pagesgit 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/agents/ocean-industries-concept-lab/openbridge-webcomponents/pages)<a href="https://agentmods.dev/agents/ocean-industries-concept-lab/openbridge-webcomponents/pages"><img src="https://agentmods.dev/badge/agents/ocean-industries-concept-lab/openbridge-webcomponents/pages.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 | $0.00013 | $0.00315 |
| Opus 5 | $0.00006 | $0.00158 |
| Sonnet 5 | $0.00003 | $0.00063 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
pages 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 yesterday.
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.
What it actually says
Page Composites
Two registered elements — obc-alert-list-page-small and
obc-alert-detail-page — that assemble many smaller components into a complete
screen.
They are compositions, not primitives. Nothing else in the library depends on them, and they should not grow behaviour of their own: if a page needs a new capability, it belongs in the component being composed, so every other consumer gets it too.
Their value is as an integration surface. A page story exercises the alert components together — spacing, overflow, and interaction between neighbours — which the individual component stories cannot show.
Consequences for changes elsewhere
Because a page renders many components at once, it is a broad blast radius for visual tests. A change to any alert component, card, or list row can move these baselines even when the component's own story is unaffected. When a page baseline moves unexpectedly, look at what it composes rather than at the page.
npx vitest run --project storybook 'page'
Related
ui-components.md— the alert, list and card components these pages assemble.a11y.md— page-level composites are where focus order and modal focus trapping actually get exercised.
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.
- yesterday First seen · 40 lines · 13 tokens per session scan A f4b3863a2b7d
pages is an agent published in the GitHub repository Ocean-Industries-Concept-Lab/openbridge-webcomponents (92 stars, last pushed today), licensed Apache-2.0. It adds 13 tokens to every session and 315 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 2026-09-03.
Other agents, from other repositories
angular-patterns
// Optional with default value readonly name = input ('').
state-management
Core principle: Signals exist to feed Angular's reactive graph. If a value has no reactive consumer, making it a signal adds tracking overhead for no benefit.
webc-generator
The webc-generator is an NX executor that automatically converts UI5 Web Components into Angular-native wrapper components. It eliminates manual maintenance of 100+ component wrappers by reading a Custom Elements Manifest (CEM) and generating the full library from it.
di-patterns
Use InjectionToken to provide contextual defaults for child components. This pattern allows parent components to influence default values without directly manipulating child component inputs.
nx-workflow
Purpose: Understanding the NX monorepo structure, development patterns, and best practices. For commands, see docs/internal/commands.md.
testing-guidelines
Agent "testing-guidelines" from SAP/fundamental-ngx, covering testing guidelines, test commands, run all tests in a library, run specific test file and examples.