agentmods.dev

mc8yp AGENTS.md

Project instructions for mc8yp, a Cumulocity IoT server that gives AI agents typed access to IoT services through one code-mode interface. Cumulocity IoT is a platform for managing connected devices and their data.

In plain words
What is it for?
Use them to search and describe API methods, read service documentation, and call typed operations exposed by the tenant’s Cumulocity services.
Why use it?
They explain how agents discover available operations and documentation without needing a large fixed list of tools or direct raw API requests.

Instructions file for CodexOpenCode

6 3d ago A scan 13,452 tokens original MIT
View the source file schplitt/mc8yp
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.

agentmods
npx agentmods add instructions/schplitt/mc8yp/agents-md
Clone the repo
git clone --depth 1 https://github.com/schplitt/mc8yp

Made for: Codex, OpenCode.

Per session 13,452 This file is loaded in full into every session.
When invoked 13,452 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.13452 $0.13452
Opus 5 $0.06726 $0.06726
Sonnet 5 $0.02690 $0.02690
Haiku 4.5 $0.01345 $0.01345

Measured 2d ago against content hash 76d60f333e8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mc8yp AGENTS.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 2d 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.

AGENTS.md · 414 lines

How it starts

The opening of the file, as written. The whole thing — 414 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project Overview

mc8yp is a Cumulocity IoT MCP server.

The project exposes a single code-mode tool to AI agents instead of a large fixed toolset:

  • codemode runs an async JavaScript function in a sandbox where API discovery, documentation search, and typed live API calls are all available as globals:
    • codemode.search(query) / codemode.describe(target?) — ranked method search and on-demand TypeScript interface rendering over operations derived from the OpenAPI specs
    • docs.search(query, opts?) / docs.read(id) — MiniSearch-backed fuzzy full-text search over spec prose (tag docs like query-language grammars, info blocks, operation/parameter descriptions)
    • c8y (core, always present) plus one namespace per service available on the tenant (e.g. dtm) — one typed method per derived operation. Namespaces are the COMPLETE sandbox surface: there is no raw-request escape hatch, and the backing protocol (OpenAPI vs MCP) is deliberately invisible to the agent
    • services that declare exposeMcpServers in their manifest are wrapped from their MCP server instead (one typed method per MCP tool) — MCP is preferred over the OpenAPI spec when a service has both, with a per-connection opt-out (mc8yp-no-mcp header / noMcp query / --no-mcp CLI flag) that falls back to the spec
    • external MCP servers supplied by the connection itself (mc8yp-mcp-server header, repeatable, JSON per entry; --mcp-server CLI flag) get a namespace too — absolute URL, their own credentials, tenant-independent, scoped to that connection/session
    • sandbox (server mode only, opt-in — disabled by default) — an in-memory shell + virtual filesystem (just-bash, core shell only: jq/awk/grep/sed/sort/sqlite3, no network, no host FS) for wrangling fetched data. Mirrors Flue's SandboxApi plus an mc8yp-only clear(). One sandbox per MCP session (persists across codemode calls, keyed by ctx.sessionId), idle-evicted after 15 minutes; nothing touches disk. A connection only gets it after opting in via the mc8yp-enable-sandbox header / enableSandbox query param — a general-purpose shell + virtual FS is a bigger blast radius than any single typed API call, so it must be explicitly requested. CLI mode never exposes it regardless — local harnesses bring their own file I/O. Backed by a swappable adapter so the provider can change later.
  • status is available only in CLI mode: it lists the active tenant, stored credentials, and the API namespaces currently visible. It accepts { refresh: true } to force a fresh API discovery on demand (noop when no tenant is active). Server mode has no in-protocol equivalent yet — use the POST /refresh-apis HTTP route for ops-driven refresh; an in-protocol server-side flow will land in a separate PR.

Read the full file on GitHub · 414 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.

  1. 2d ago First seen · 414 lines · 13,452 tokens per session scan A 76d60f333e8a

Subscribe to this mod's changes

mc8yp AGENTS.md is an instructions file published in the GitHub repository schplitt/mc8yp (6 stars, last pushed 3d ago), licensed MIT. It adds 13,452 tokens to every session, about $0.0673 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.

Backend and APIsResearchWriting and docscumulocitycumulocity-agentcumulocity-iotmcp
Related

Other instructions, from other repositories

cumulocity-dynamic-mapper AGENTS.md

Instructions for Cumulocity-IoT/cumulocity-dynamic-mapper, covering cumulocity dynamic mapper — agent guidelines, module structure, documentation map, quick commands and backend (java 21, maven).

Cumulocity-IoT/cumulocity-dynamic-mapper · 687 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens