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.
npx agentmods add instructions/alpayc/abfall-mcp-server/agents-mdgit clone --depth 1 https://github.com/AlpayC/abfall-mcp-serverWrote 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/alpayc/abfall-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/alpayc/abfall-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/alpayc/abfall-mcp-server/agents-md.svg" alt="Measured on agentmods" 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 | $0.01368 | $0.01368 |
| Opus 5 | $0.00684 | $0.00684 |
| Sonnet 5 | $0.00274 | $0.00274 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade A, and why
abfall-mcp-server 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.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notes for coding agents
MCP server for German waste collection calendars. This is the operational summary; CONTRIBUTING.md is written for humans and carries more context. Documentation is English, the domain code is German — see Style below.
Setup
git submodule update --init --depth 1 # without this the data source is missing
uv sync
Commands
uv run pytest # ~100 tests, run offline, under 1 s
uv run ruff check src scripts tests # lint; --fix clears most of it
uv run python scripts/build_registry.py # rebuild data/providers.json
uv run abfall-mcp-server # server, stdio
uv run abfall-mcp-server --http # server, HTTP on 127.0.0.1:8000
scripts/smoke.py talks to the real portals. It is not a test but a
measurement, and every run puts load on someone else's servers. Use it
deliberately, never in a loop, never in CI.
The one principle
When in doubt, ask — do not guess.
A wrongly guessed town or street will cheerfully return the neighbouring municipality's collection calendar. That is a wrong answer that looks like a right one — the most expensive failure here, because nobody notices it. Concretely:
- Assignments are only accepted above a threshold:
resolve.CONFIDENCE_THRESHOLDfor argument values,server.MIN_AUTO_FETCHfor picking a provider. - Below that, the list of options goes back to the caller
(
status: "rueckfrage"). - Do not lower these thresholds to make a test address work. If you do, a test must demonstrate that nothing wrong slips through.
Traps
Every one of these has already bitten this project.
1. Never put the submodule on sys.path. Its parent directory contains
Home Assistant glue including its own calendar.py, which shadows the stdlib
module — requests falls apart on import. wcs.ensure_importable() registers
only the inner package in sys.modules on purpose. Do not "simplify" it.
2. data/providers.json belongs to the submodule commit. Change one,
rebuild the other and commit them together. CI recomputes this and fails
otherwise. The build is deterministic and needs no network.
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.
- 3d ago First seen · 136 lines · 1,368 tokens per session scan A 899d970fb156
abfall-mcp-server AGENTS.md is an instructions file published in the GitHub repository AlpayC/abfall-mcp-server (1 stars, last pushed 7d ago), licensed MIT. It adds 1,368 tokens to every session, about $0.0068 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
mcp-server-excel coverage-prevention-strategy.instructions.md
Instructions for sbroenne/mcp-server-excel, covering generated surface coverage, contract change workflow, required checks and common incomplete changes.
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
openrouter-mcp-multimodal AGENTS.md
Instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
autotask-mcp dev_workflow.instructions.md
Guide for using Taskmaster to manage task-driven development workflows.
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
ntfy-mcp-server AGENTS.md
Instructions for cyanheads/ntfy-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.