add-resolver

add-resolver is a command for Claude Code from AlpayC/abfall-mcp-server. It costs 12 tokens per session (616 once invoked), scanned A, original, MIT.

A command for adding an internal-ID resolver to a waste-authority integration. Some authorities require identifiers for places or houses that cannot be worked out from an address alone.

In plain words
What is it for?
Use it to investigate an authority's required identifiers, inspect the relevant source and wizard, and add and verify the matching resolver.
Why use it?
It guides developers toward a resolver only when the authority truly needs one, avoiding a resolver that would not fix the actual problem.

Command for Claude Code

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 commands/alpayc/abfall-mcp-server/add-resolver
Clone the repo
git clone --depth 1 https://github.com/AlpayC/abfall-mcp-server

Made for: Claude Code.

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 add-resolver

README.md
[![agentmods](https://agentmods.dev/badge/commands/alpayc/abfall-mcp-server/add-resolver.svg)](https://agentmods.dev/commands/alpayc/abfall-mcp-server/add-resolver)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 616 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00012 $0.00616
Opus 5 $0.00006 $0.00308
Sonnet 5 $0.00002 $0.00123
Haiku 4.5 $0.00001 $0.00062

Measured 3d ago against content hash b61eef2f220d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

.claude/commands/add-resolver.md · 59 lines

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:

  1. 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.py already handles it — the bug is elsewhere, and a resolver is the wrong fix.

  2. Read the source module under vendor/hacs_waste_collection_schedule/custom_components/waste_collection_schedule/waste_collection_schedule/source/ to see which arguments Source.__init__ takes and how they are used.

  3. 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.

  4. Verify the portal live before writing anything. Reproduce each step with requests and confirm the identifier you get matches the module's TEST_CASES. That check caught a wrong endpoint once already.

  5. Write the resolver in src/abfall_mcp_server/lookup.py, following resolve_hamburg / resolve_bsr:

    • signature (default_args, address, picker, *, min_confidence, timeout)
    • address carries city, district, street, house_number
    • make every choice through _choose(...) so picker decides and the project-wide confidence threshold applies — never pick an option directly
    • register it in RESOLVERS
  6. Test it end to end against a real address, through the MCP tool rather than the resolver alone.

  7. Add tests in tests/test_lookup.py for the decision logic — no network. Then run:

    uv run ruff check src scripts tests && uv run pytest
    
  8. Update the authority table in README.md, README.de.md and the CHANGELOG.md entry under Unreleased.

Do not commit unless asked.

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 · 59 lines · 12 tokens per session scan A b61eef2f220d

Subscribe to this mod's changes

add-resolver is a command published in the GitHub repository AlpayC/abfall-mcp-server (1 stars, last pushed 6d ago), licensed MIT. It adds 12 tokens to every session and 616 once invoked, about $0.0001 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.