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/derekslinz/meta-data-mcp/agents-mdgit clone --depth 1 https://github.com/derekslinz/meta-data-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/derekslinz/meta-data-mcp/agents-md)<a href="https://agentmods.dev/instructions/derekslinz/meta-data-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/derekslinz/meta-data-mcp/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 5.1 | $0.01623 | $0.01623 |
| Opus 5 | $0.00812 | $0.00812 |
| Sonnet 5 | $0.00325 | $0.00325 |
| Haiku 4.5 | $0.00162 | $0.00162 |
Grade A, and why
meta-data-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 5d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — meta-data-mcp
Working guide for AI agents (Copilot, Claude, etc.) contributing to this repo.
What this repo is
One MCP server (meta-data-mcp) that exposes 66 open-data plugins under a single tool
namespace. An LLM calls opendata_providers_find to discover which plugin to use, then
calls that plugin's tool directly. The server can also scaffold and hot-load new plugins
at runtime via opendata_plugins_draft + opendata_plugins_create.
Codebase map
meta_data_mcp/
cli.py — Click CLI (run, setup, remove, cleanup, inspect, list, info, version)
registry.py — REGISTRY list of ProviderEntry dataclasses; DOMAINS/REGIONS vocabs
routing.py — RoutingEngine: multi-criteria provider ranking (token, fuzzy, semantic, metadata)
utils.py — http_get(), TTL cache, MCP server factory, to_json_text()
citations.py — Per-call source-citation manifest (recording spans, URL redaction)
harmonize.py — Cross-provider normalization: geo (ISO 3166) + period + frequency
harmonize_data.py — Generated ISO 3166 concordance (via tools/generate_concordance.py)
federate.py — Pure federation transforms behind opendata_federate_query/compare
providers/
__template__.py — Canonical pattern every plugin must follow
{id}.py — One file per plugin (66 total)
providers/meta_data_mcp.py — Meta tools: find-providers, draft-spec, create-plugin, etc.
tools/
generate_provider.py — CLI generator: YAML spec → provider module + test file
generate_concordance.py — Regenerates meta_data_mcp/harmonize_data.py from ISO 3166 source
specs/ — YAML specs for generated plugins
tests/
providers/test_{id}.py — Unit tests (mock at httpx.get boundary)
live/ — Live integration tests (skip by default; run with -m live)
test_routing.py — RoutingEngine unit tests
test_registry.py — Registry validation tests
test_generator.py — Generator tests
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.
- 5d ago First seen · 160 lines · 1,623 tokens per session scan A 3d325b969887
meta-data-mcp AGENTS.md is an instructions file published in the GitHub repository derekslinz/meta-data-mcp (5 stars, last pushed 2d ago), licensed MIT. It adds 1,623 tokens to every session, about $0.0081 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
ExtremeRouter AGENTS.md
AGENTS.md instructions for rsalmn/ExtremeRouter, covering extremerouter — lead engineer agent, core philosophy, thinking process, critical thinking and coding standards.
ClaudeCode-Model-Rotator CLAUDE.md
Claude Code instructions for tullextraterrestrial3175/ClaudeCode-Model-Rotator, covering claude code multi-provider rotator - project guide, project overview, core architecture, files and key components.
ClaudeCode-Model-Rotator CLAUDE.md
Claude Code instructions for BheeshamKS/ClaudeCode-Model-Rotator, covering claude code multi-provider rotator - project guide, project overview, core architecture, files and key components.
mcp-execution mcp-wasm-runtime.instructions.md
Instructions for bug-ops/mcp-execution, covering copilot instructions: mcp-wasm-runtime, security - critical, security principles, security configuration and host function safety.
outlook-mcp CLAUDE.md
Claude Code instructions for ryaker/outlook-mcp, covering claude.md, development commands, architecture overview, core structure and modules.
MCPs copilot-instructions.md
Copilot instructions for AceDataCloud/MCPs, covering copilot sync instructions for acedatacloud mcps, repository structure, source of truth, what to sync and rules.