What is eval-opaque-words?

A task-specific agent that answers one question about Dutch buildings through a connected data server. It must use only that server and reports its answer and tool calls in a fixed format.

Use it as one answering component in an evaluation of building-data questions. It is not intended for direct, general-purpose use.

It keeps a building-data answer limited to the available source instead of allowing general knowledge or guesses. It also makes the sources and inputs used easy to inspect.

How DaveGold/mcp-metadata-demo configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to DaveGold/mcp-metadata-demo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/DaveGold/mcp-metadata-demo/main/.claude/agents/eval-opaque-words.md

Clone the repo

git clone --depth 1 https://github.com/DaveGold/mcp-metadata-demo

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/davegold/mcp-metadata-demo/eval-opaque-words/github.svg)](https://agentmods.dev/agents/davegold/mcp-metadata-demo/eval-opaque-words)

Your own site

<a href="https://agentmods.dev/agents/davegold/mcp-metadata-demo/eval-opaque-words"><img src="https://agentmods.dev/badge/agents/davegold/mcp-metadata-demo/eval-opaque-words/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/davegold/mcp-metadata-demo/eval-opaque-words"><img src="https://agentmods.dev/badge/agents/davegold/mcp-metadata-demo/eval-opaque-words.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 245 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00041	$0.00245
Opus 5.5	$0.00016	$0.00098
Sonnet 5.5	$0.00008	$0.00049
Haiku 4.5	$0.00004	$0.00024

Measured 1mo ago against content hash 48b66582111c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

eval-opaque-words 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 1mo 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/agents/eval-opaque-words.md · 19 lines

What it actually says

You are answering a single question from a user about Dutch buildings, using the tools available to you.

Answer the question as well as the tools allow. If the tools cannot answer it, say so plainly rather than guessing.

Return exactly this, and nothing else:

ANSWER: <your answer to the user's question, in at most four sentences> CALLS: TOOLS: <comma-separated tool names you called, in order, or "none"> PARAMS: <the arguments of each call, as compact JSON, in order, or "none">

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.

1mo ago First seen · 19 lines · 41 tokens per session scan A 48b66582111c

Subscribe to this mod's changes

eval-opaque-words is an agent published in the GitHub repository DaveGold/mcp-metadata-demo (5 stars, last pushed 11d ago), licensed MIT. It adds 41 tokens to every session and 245 once invoked, about $0.0002 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 2026-09-21.

Research ai-tooling bag claude energy-label kadaster mcp

eval-opaque-words next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
eval-opaque-wordsDaveGold/mcp-metadata-demo	Agent	5	11d ago	MIT	A	41	Claude Code
qa-executorhmj1026/dhpk	Agent	2	yesterday	MIT	A	108	Claude Code
smoke-testerhmj1026/dhpk	Agent	2	yesterday	MIT	A	155	Claude Code
codex-reviewerhmj1026/dhpk	Agent	2	yesterday	MIT	A	26	Claude Code
copilotivanhoinacki/team-exp-claude-config	Agent	2	1mo ago	MIT	A	69	Claude Code
researcherivanhoinacki/team-exp-claude-config	Agent	2	1mo ago	MIT	A	61	Claude Code
reviewerivanhoinacki/team-exp-claude-config	Agent	2	1mo ago	MIT	A	48	Claude Code

mcp-metadata-demo: Agent for Claude Code