mcp-pirsch AGENTS.md

mcp-pirsch AGENTS.md is an instructions file for Codex, OpenCode from verygoodplugins/mcp-pirsch. It costs 223 tokens per session, scanned A, original, MIT.

Contributor instructions for mcp-pirsch, a local server that lets coding tools read Pirsch website-analytics data. They define its commands, design limits, error handling, and release process.

In plain words
What is it for?
Checking types, linting, testing, building, inspecting the available tools, and following the project's rules when changing the server.
Why use it?
They help contributors preserve a read-only server with a stable four-tool interface and avoid exposing credentials or private account details.

Instructions file for CodexOpenCode

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/verygoodplugins/mcp-pirsch/agents-md
Clone the repo
git clone --depth 1 https://github.com/verygoodplugins/mcp-pirsch

Made for: Codex, OpenCode.

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.

agentmods badge for mcp-pirsch AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/verygoodplugins/mcp-pirsch/agents-md.svg)](https://agentmods.dev/instructions/verygoodplugins/mcp-pirsch/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/verygoodplugins/mcp-pirsch/agents-md"><img src="https://agentmods.dev/badge/instructions/verygoodplugins/mcp-pirsch/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 223 This file is loaded in full into every session.
When invoked 223 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 $0.00223 $0.00223
Opus 5 $0.00112 $0.00112
Sonnet 5 $0.00045 $0.00045
Haiku 4.5 $0.00022 $0.00022

Measured 3d ago against content hash 51c88aae443f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-pirsch 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 3d 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 · 18 lines

What it actually says

MCP Pirsch contributor guide

Commands

Run npm run typecheck, npm run lint, npm test, and npm run build before handing off changes. Use npx -y @modelcontextprotocol/inspector@latest --cli node dist/index.js --method tools/list --format json for an MCP surface check.

Design constraints

  • Keep the server stdio-only and read-only.
  • Keep exactly four public tools unless the maintainers approve an API expansion.
  • Tool handlers must declare Zod input/output schemas, read-only annotations, structured content, matching JSON text, and isError: true for expected failures.
  • Do not validate credentials at process start, select a domain automatically, return raw domain/account metadata, log secrets, or include raw upstream error bodies.
  • Use PIRSCH_DEFAULT_DOMAIN_ID only as an explicit configured default; otherwise require domainId.

Delivery

Do not publish packages or registry entries from local work. The release workflow publishes a release tag to npm first, then the MCP Registry through GitHub OIDC.

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. 3d ago First seen · 18 lines · 223 tokens per session scan A 51c88aae443f

Subscribe to this mod's changes

mcp-pirsch AGENTS.md is an instructions file published in the GitHub repository verygoodplugins/mcp-pirsch (1 stars, last pushed 7d ago), licensed MIT. It adds 223 tokens to every session, about $0.0011 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.