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/docgengit 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/docgen)<a href="https://agentmods.dev/instructions/ocean-industries-concept-lab/openbridge-webcomponents/docgen"><img src="https://agentmods.dev/badge/instructions/ocean-industries-concept-lab/openbridge-webcomponents/docgen.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 | $0.00401 | $0.00401 |
| Opus 5 | $0.00200 | $0.00200 |
| Sonnet 5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
openbridge-webcomponents docgen.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.
What it actually says
Doc Generator CLI
script/docgen/ is a small CLI that drafts JSDoc for a source file using an
OpenAI model.
| File | Role |
|---|---|
docs-gen.ts |
The CLI itself |
prompt-system.txt |
The shared system prompt |
README.md |
Setup, dependencies and usage |
It reads the .ts plus its sibling .stories.ts and .css, auto-detects which
of the three documentation patterns applies (concrete component, pure function
module, abstract base class), and writes a *.generated.ts review copy next
to the original.
It never edits the original
The review-copy design is the point: output is a draft for a human to diff and
merge, not a change. Do not wire this into a build step, a lint rule, or a
pre-commit hook, and do not commit *.generated.ts files.
Keep the prompt aligned with the rules
prompt-system.txt encodes the same conventions as
jsdoc.md — the section order, the tone rule that forbids
domain qualifiers, the TODO(designer) placeholder, and the structured
@slot / @fires tag block.
When the JSDoc rules change, update the prompt too. Nothing enforces the
link, so a rule added to jsdoc.md alone will be silently contradicted by every
subsequent draft. Generated output still has to pass npm run lint:slots like
any hand-written JSDoc.
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 · 42 lines · 401 tokens per session scan A b5fd819b1e6d
openbridge-webcomponents docgen.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 401 tokens to every session, about $0.0020 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.
fundamental-ngx CLAUDE.md
Claude Code instructions for SAP/fundamental-ngx, covering fundamental ngx, architecture, commands, build / lint / test a library and affected only (prefer this for validation).
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.
fundamental-ngx copilot-instructions.md
Copilot instructions for SAP/fundamental-ngx, covering github copilot instructions and quick links.
primitives angular.instructions.md
Instructions for radix-ng/primitives, covering typescript best practices, angular best practices, components, state management and templates.
primitives nx.instructions.md
Instructions for radix-ng/primitives, covering general guidelines and generation guidelines.