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 skills add quantDIY/GERP --skill docsgit clone --depth 1 https://github.com/quantDIY/GERPWrote 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/skills/quantdiy/gerp/docs)<a href="https://agentmods.dev/skills/quantdiy/gerp/docs"><img src="https://agentmods.dev/badge/skills/quantdiy/gerp/docs/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/skills/quantdiy/gerp/docs"><img src="https://agentmods.dev/badge/skills/quantdiy/gerp/docs.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 | $0.00014 | $0.00322 |
| Opus 5.5 | $0.00006 | $0.00129 |
| Sonnet 5.5 | $0.00003 | $0.00064 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
COAMS 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 1mo 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
COAMS (GERP Module)
Overview
COAMS is an AI-First, ignorant content engine injected into the GERP Matrix. It does not speak JSON; it speaks native Markdown. When you (the Agent) interact with COAMS, you operate physically isolated Vector shards utilizing pgvector stored within AlloyDB.
Architectural Constraints (DO NOT VIOLATE)
- Zero Broken Links: COAMS mathematically enforces the Agent-Index. Every
doc:uuidlink you author in Markdown MUST exist within the isolatedchannel_idbounds OR the commit will violently reject the transaction. - Ignorant Domain: The pure Go
internal/coamslayer knows nothing about HTTP or the existence of AI. It operates purely on interfaces. - Partition Pruning: You cannot search outside your immediate IAM token boundary. The AlloyDB SQL planner will literally drop vectors outside your
channel_id. - Verbosity: All documents carry heavy metadata matching the IAM footprint.
Executing the Publish Saga Lifecycle
To persist arbitrary markdown documents into COAMS:
gerp coams sync ./docs
This triggers the orchestration layers to extract ASTs, run Graph Verification (verifier.go), chunk texts, invoke Vertex AI, save vectors, and automatically regenerate the GraphQL Broadcast schema dynamically.
Man Pages
For deeper integration, execute gerp coams gen-man to render system operator manuals natively.
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.
- 1mo ago First seen · 27 lines · 14 tokens per session scan A 968e5278927e
COAMS is a skill published in the GitHub repository quantDIY/GERP (4 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 322 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
markitdown
Converts heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.
llamaindex
Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM…
xberg-picking-a-format
Use when choosing an output format for extracted documents — plain text, markdown, djot, HTML, JSON, or DocTags. Maps consumer (LLM, parser, archive) to the right --format / --content-format pair.
kb-retriever
A retrieval and question-answering assistant for a local folder of documents, including Markdown, text, PDFs, and spreadsheets.
azure-ai
Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech.
bailian-kb
A command-line manager for Alibaba Cloud Bailian knowledge bases, which are collections of documents prepared for search and question answering. It handles the stored documents, search services, text chunks, and data-centre files rather than everyday searches.