eea-climate-data-mcp: Instructions file for Codex

AGENTS.md

eea-climate-data-mcp AGENTS.md is an instructions file for Codex, OpenCode from kalcifield/eea-climate-data-mcp. It costs 783 tokens per session, scanned A, original, MIT.

Repository instructions for a Python service that provides European Environment Agency climate data through a command-line interface and an MCP server. The European Environment Agency is an EU body that publishes environmental information.

In plain words
What is it for?
Use them when developing, testing, formatting, type-checking, or releasing the climate-data service.
Why use it?
They keep data models, workflows, SQL checks, interfaces, tests, and release steps organized consistently.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is kalcifield/eea-climate-data-mcp's own configuration. It tells Codex and OpenCode how to work on eea-climate-data-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything eea-climate-data-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kalcifield/eea-climate-data-mcp. 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/kalcifield/eea-climate-data-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/kalcifield/eea-climate-data-mcp

Made for: Codex, OpenCode.

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 eea-climate-data-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kalcifield/eea-climate-data-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/kalcifield/eea-climate-data-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kalcifield/eea-climate-data-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/kalcifield/eea-climate-data-mcp/agents-md/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.

agentmods 80×15 button for eea-climate-data-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kalcifield/eea-climate-data-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/kalcifield/eea-climate-data-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 783 This file is loaded in full into every session.
When invoked 783 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00783 $0.00783
Opus 5.5 $0.00313 $0.00313
Sonnet 5.5 $0.00157 $0.00157
Haiku 4.5 $0.00078 $0.00078

Measured 2mo ago against content hash a23828b26653, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

eea-climate-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 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.

AGENTS.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure

Python uses the src layout under src/eea_climate_data/. Keep typed data contracts in models.py, workflows in service.py, SQL safety in sql_validation.py, upstream wire behavior in discodata.py, and verified EEA table semantics in profile.py. Keep cli.py and mcp_server.py thin; both must call the same ClimatePolicyService methods. Design findings and live evidence belong in docs/.

Development Commands

Use Python 3.11+ and uv:

uv sync --extra test
uv run eu-climate --help
uv run eea-climate-data-mcp
uv run pytest -q
uv run ruff format --check src tests
uv run ruff check src tests
uv run mypy src tests

Release with scripts/release {patch|minor|major}. GitHub Actions publishes to PyPI through the pypi environment after the GitHub Release is created.

Run uv run python scripts/live_smoke.py only when explicitly validating the public service. Keep live probes small, bounded, read-only, and separate from routine tests.

Code and Interface Conventions

Use type annotations and Pydantic models at public boundaries. Modules, functions, and variables use snake_case; classes and models use PascalCase. Preserve upstream field names in provider payloads and normalized semantics in domain models. Machine-readable output goes to stdout; diagnostics go to stderr. JSON and JSONL output must remain semantically equivalent. Avoid provider logic in CLI or MCP adapters.

SQL Safety

Never weaken the single-statement, SELECT-only, database/version allowlist, fully-qualified-table, row-bound, page-size, timeout, computed-alias, or system-schema guardrails. Continue using a T-SQL parser; regex alone must not authorize queries. Block DDL, DML, execution, transactions, SELECT INTO, CTEs, and unsupported system objects. Warn when pagination lacks deterministic ordering. Do not log raw SQL containing user literals. Query results are deliberately not cached unless a reviewed design changes that policy.

Read the full file on GitHub · 75 lines

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. 2mo ago First seen · 75 lines · 783 tokens per session scan A a23828b26653

Subscribe to this mod's changes

eea-climate-data-mcp AGENTS.md is an instructions file published in the GitHub repository kalcifield/eea-climate-data-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 783 tokens to every session, about $0.0031 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.

Related

eea-climate-data-mcp AGENTS.md compared with instructions from other repositories

eea-climate-data-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
eea-climate-data-mcp AGENTS.mdkalcifield/eea-climate-data-mcpInstructions file03mo agoMITA783Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode