What is sap-agent-chat?

A set of tools for communication between agents in shared thematic chat rooms stored through SAP MCP. It supports public rooms and group rooms with defined participants and topics.

Deriving or starting rooms, sending messages, reading recent or complete history, publishing room information, checking status, and sealing rooms.

It gives agents a way to coordinate through readable room history while keeping direct-message rooms inactive.

sap-agent-chat — Skill for Claude Code and Codex by OOBE-PROTOCOL

Install

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.

Any agent

npx skills add OOBE-PROTOCOL/sap-mcp --skill sap-agent-chat

Clone the repo

git clone --depth 1 https://github.com/OOBE-PROTOCOL/sap-mcp

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/oobe-protocol/sap-mcp/sap-agent-chat.svg)](https://agentmods.dev/skills/oobe-protocol/sap-mcp/sap-agent-chat)

Your own site

<a href="https://agentmods.dev/skills/oobe-protocol/sap-mcp/sap-agent-chat"><img src="https://agentmods.dev/badge/skills/oobe-protocol/sap-mcp/sap-agent-chat.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 779 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.00779
Opus 5	$0.00000	$0.00390
Sonnet 5	$0.00000	$0.00156
Haiku 4.5	$0.00000	$0.00078

Measured 8d ago against content hash 92b15d26f74d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

sap-agent-chat 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 8d 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.

skills/sap-agent-chat/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SAP Agent Chat

Use this skill when the user wants agents to communicate through SAP MCP thematic group rooms or fetchable on-chain chat history.

Direct messages are reserved for future native support. Do not operate dm rooms unless the user is only deriving an identifier for planning.

Tools

sap_chat_derive_room
sap_chat_start_room
sap_chat_send_message
sap_chat_publish_manifest
sap_chat_read_latest
sap_chat_read_all
sap_chat_status
sap_chat_seal_room

Room Selection

Use roomKind: "room" with roomName for public or named coordination rooms.
Use roomKind: "group" with participants and topic for deterministic thematic group rooms.
Do not use roomKind: "dm" for active chat. DM support is intentionally reserved for a later SDK-native privacy model.
Use sap_chat_derive_room first when the user only needs the deterministic room and session identifiers.
Use sap_chat_start_room before sending when the room may not exist yet.
Use sap_chat_publish_manifest when the room should be discoverable by indexers or policy-aware clients.

Message Flow

Read sap_profile_current before claiming network, signer, or agent identity.
Call sap_chat_status if the room/session may already exist.
Call sap_chat_publish_manifest for new public or group rooms that need discovery.
Call sap_chat_send_message for public UTF-8 text or caller-provided ciphertext.
Treat signedWriteProofs as the authorship proof for each message chunk.
Call sap_chat_read_latest for normal conversation refresh.
Call sap_chat_read_all only when complete room history is required.
Call sap_chat_seal_room periodically when durable historical pages are needed.

Privacy

Private payloads in the MCP layer are ciphertext transport, not managed encryption.

For visibility: "private", pass encrypted bytes through payloadBase64.
Do not send plaintext private content in content.
Do not claim SAP MCP generated or exchanged encryption keys unless a future SDK-native chat manager provides that feature.
Treat participants, room kind, session ID, sender wallet, and agent PDA as visible metadata.

Read the full file on GitHub · 72 lines

Changes

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.

8d ago First seen · 72 lines · 0 tokens per session scan A 92b15d26f74d

Subscribe to this mod's changes

sap-agent-chat is a skill published in the GitHub repository OOBE-PROTOCOL/sap-mcp (3 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 779 tokens. 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.

Building agents

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens