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 skills/quantdiy/gerp/docsnpx skills add quantDIY/GERP --skill docsgit clone --depth 1 https://github.com/quantDIY/GERPWhat 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 | $0.00014 | $0.00322 |
| Opus 5 | $0.00007 | $0.00161 |
| Sonnet 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 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
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.
- yesterday First seen · 27 lines · 14 tokens per session scan A 968e5278927e
COAMS is a skill published in the GitHub repository quantDIY/GERP (2 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 322 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 2026-08-31.
Other skills, from other repositories
comms-context
Fetch on-call and discussion context from Slack threads and PagerDuty incidents — participants, timeline, and status. Auto-loads on Slack permalinks or PagerDuty incident references. Keywords — Slack, thread, PagerDuty, on-call.
format-specific-extraction
Format-specific document extraction workflows.
api-server-mcp
REST API server and MCP protocol integration.
octo-drive
Octo Drive — spaces, folders, file upload/download, online-document mounts, share links, invites, IM-attachment transfer. Works with a bot token or a user API key; the CLI routes by token kind. Load after octo-shared.
octo-mail
OCTO Agent Mail operations for reading, searching, policy-aware sending, preparing drafts, and checking delivery status exclusively through octo-cli.
octo-docs
Docs domain — create and govern documents, read and incrementally edit a doc's live body, read and batch-edit spreadsheet cells (dims + images), read and batch-edit whiteboard scenes, members and sharing, inline comments, versions/snapshots, and attachment metadata as a bot. Load after octo-shared.