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.
git 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/commands/alpayc/abfall-mcp-server/add-resolver)<a href="https://agentmods.dev/commands/alpayc/abfall-mcp-server/add-resolver"><img src="https://agentmods.dev/badge/commands/alpayc/abfall-mcp-server/add-resolver/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/commands/alpayc/abfall-mcp-server/add-resolver"><img src="https://agentmods.dev/badge/commands/alpayc/abfall-mcp-server/add-resolver.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 | $0.00012 | $0.00616 |
| Opus 5.5 | $0.00005 | $0.00246 |
| Sonnet 5.5 | $0.00002 | $0.00123 |
| Haiku 4.5 | $0.00001 | $0.00062 |
Grade A, and why
add-resolver 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 2mo 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.
What it actually says
Add an ID resolver for: $ARGUMENTS
This applies to authorities that require internal identifiers which cannot be
derived from an address — standort in Dresden, idHouseNumber in Leipzig,
streetnr in Stuttgart. Work through it in this order:
-
Confirm it is the right kind of problem. Look up the authority and check what it actually demands:
uv run python -c "from abfall_mcp_server import registry; [print(p.id, '|', p.title, '| open:', p.open_args) for p, _ in registry.search('$ARGUMENTS', limit=5)]"If it needs a plain-text street or town rather than an identifier, the generic suggestion loop in
resolve.pyalready handles it — the bug is elsewhere, and a resolver is the wrong fix. -
Read the source module under
vendor/hacs_waste_collection_schedule/custom_components/waste_collection_schedule/waste_collection_schedule/source/to see which argumentsSource.__init__takes and how they are used. -
Read the upstream wizard for the same name under
.../wizard/, if one exists. It shows the path through the portal. Treat it as a lead, not as truth — the Hamburg wizard was already stale, the portal had moved to a JavaScript component. -
Verify the portal live before writing anything. Reproduce each step with
requestsand confirm the identifier you get matches the module'sTEST_CASES. That check caught a wrong endpoint once already. -
Write the resolver in
src/abfall_mcp_server/lookup.py, followingresolve_hamburg/resolve_bsr:- signature
(default_args, address, picker, *, min_confidence, timeout) addresscarriescity,district,street,house_number- make every choice through
_choose(...)sopickerdecides and the project-wide confidence threshold applies — never pick an option directly - register it in
RESOLVERS
- signature
-
Test it end to end against a real address, through the MCP tool rather than the resolver alone.
-
Add tests in
tests/test_lookup.pyfor the decision logic — no network. Then run:uv run ruff check src scripts tests && uv run pytest -
Update the authority table in
README.md,README.de.mdand theCHANGELOG.mdentry under Unreleased.
Do not commit unless asked.
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.
- 2mo ago First seen · 59 lines · 12 tokens per session scan A b61eef2f220d
add-resolver is a command published in the GitHub repository AlpayC/abfall-mcp-server (1 stars, last pushed 3d ago), licensed MIT. It adds 12 tokens to every session and 616 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.