Borrowing it
Nothing to install: this file belongs to consetto/calmcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/consetto/calmcp/main/AGENTS.mdgit clone --depth 1 https://github.com/consetto/calmcpWrote 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/consetto/calmcp/agents-md)<a href="https://agentmods.dev/instructions/consetto/calmcp/agents-md"><img src="https://agentmods.dev/badge/instructions/consetto/calmcp/agents-md/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/instructions/consetto/calmcp/agents-md"><img src="https://agentmods.dev/badge/instructions/consetto/calmcp/agents-md.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 | $0.01248 | $0.01248 |
| Opus 5.5 | $0.00499 | $0.00499 |
| Sonnet 5.5 | $0.00250 | $0.00250 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
calmcp 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 18d 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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
calmcp: guide for contributors and coding agents
calmcp is an MCP server for SAP Cloud ALM. The README describes what it does; this file describes how to change it without breaking what models rely on.
Principles
- Wrong-but-plausible is the failure to avoid. A truncated response, a silently dropped filter or
an ignored parameter produces an answer that looks authoritative and is wrong. calmcp therefore
rejects what it cannot honour (unknown parameters, unknown fields,
$filteron a REST resource), withholds oversized payloads with a summary (src/tools/result.ts), and marks incomplete countscomplete: false. - Writes are opt-in and narrow. Read-only by default.
calm_createonly creates; there is no PUT and no DELETE insrc/calm/httpClient.ts, and a write is never retried. Write payloads are strict schemas transcribed from the OpenAPI specs. - Text from Cloud ALM is untrusted. Titles, descriptions and documents are written by other people and may carry instructions. Never let such text decide what calmcp writes.
Layout
| Path | What lives there |
|---|---|
src/index.ts, src/server.ts |
CLI entry, transports, server assembly, instructions sent to clients, which tools a caller gets |
src/transport/ |
stdio and Streamable HTTP (auth, CORS, rate limit) |
src/auth/ |
OAuth2 client credentials, sandbox API key, BTP destination |
src/calm/ |
HTTP client per Cloud ALM service, OData query building, scope hints for 403 |
src/tools/index.ts |
Tool registration: names, descriptions, annotations, input schemas |
src/tools/schemas.ts |
Tool input schemas (zod), made strict at registration |
src/tools/registry/ |
calm_list and calm_get resources: one entry per Cloud ALM collection or entity |
src/tools/create.ts |
calm_create resources and their strict payload schemas |
src/tools/analyticsCatalog.ts, recipes.ts, codeLists.ts |
Static knowledge surfaced by calm_resources |
src/tools/counting.ts, aggregate.ts, paging.ts |
count_only, group_by and the paging behind them |
YAML/ (gitignored) |
The Cloud ALM OpenAPI specs; see docs/API_VERSIONS.md |
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.
- 18d ago First seen · 76 lines · 1,248 tokens per session scan A 349939ca3efd
calmcp AGENTS.md is an instructions file published in the GitHub repository consetto/calmcp (3 stars, last pushed 5d ago), licensed MIT. It adds 1,248 tokens to every session, about $0.0050 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 2026-10-02.
Other instructions, from other repositories
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.