Borrowing it
Nothing to install: this file belongs to bitcoinaustria/pretix-agent-mcp. 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/bitcoinaustria/pretix-agent-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/bitcoinaustria/pretix-agent-mcpWrote 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/bitcoinaustria/pretix-agent-mcp/agents-md)<a href="https://agentmods.dev/instructions/bitcoinaustria/pretix-agent-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/bitcoinaustria/pretix-agent-mcp/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/bitcoinaustria/pretix-agent-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/bitcoinaustria/pretix-agent-mcp/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 | $0.01785 | $0.01785 |
| Opus 5 | $0.00892 | $0.00892 |
| Sonnet 5 | $0.00357 | $0.00357 |
| Haiku 4.5 | $0.00178 | $0.00178 |
Grade A, and why
pretix-agent-mcp 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 7d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in pretix-agent-mcp
An MCP server that lets AI agents administer a pretix instance without the pretix API token ever reaching the agent. What the project is and where it is going: PRD.md (product spec and north star) and README.md (operator-facing).
This file is the delta — what you cannot get from reading the code quickly.
Quality gates
make setup # once
make ci # ruff check + ruff format --check + pytest -q
make ci is exactly what CI runs, on Python 3.11 and 3.13. Line length 110. The test
harness and what a change owes in tests: TESTING.md. No new runtime
dependencies without a reason in the PR body — the current four are mcp, httpx,
uvicorn, starlette.
Non-negotiables
These are the reason the project exists. A change that weakens one is wrong even if tests pass, and each is enforced by tests that will fail loudly:
- No generic HTTP/API/request tool, ever. Not "just for debugging", not behind a config flag. Every pretix capability is a named, schema'd tool.
- Every agent-supplied value that becomes a URL path segment is validated through
validate.py —
app.check_event()for event slugs,object_id()for numeric ids,order_code()for order codes. This is what makes "arbitrary REST access is impossible" true, not a nicety. - The pretix token never leaves the server: not in a result, an exception message, a log line, an audit record, or a tool parameter. Never interpolate the httpx client or its headers into a message.
- Defaults stay closed: localhost bind,
readonly,PII_MODE=redacted, no writes. Every relaxation is an explicit operator config change. - Approval stays out of band. No tool may approve, or set the approval state of, a pending action — a prompt-injected agent would just call it. The CLI on the server is the only approval surface.
- Changes to validation, redaction, the capability gate, the approval store or auth need tests in the same PR. See TESTING.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.
- 7d ago First seen · 121 lines · 1,785 tokens per session scan A 7ac86f9ec932
pretix-agent-mcp AGENTS.md is an instructions file published in the GitHub repository bitcoinaustria/pretix-agent-mcp (0 stars, last pushed 15d ago), licensed MIT. It adds 1,785 tokens to every session, about $0.0089 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 instructions, from other repositories
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.
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.
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).
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).
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.
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.