Borrowing it
Nothing to install: this file belongs to ambiental-media/jor-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.
curl -O https://raw.githubusercontent.com/ambiental-media/jor-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/ambiental-media/jor-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/ambiental-media/jor-mcp/agents-md)<a href="https://agentmods.dev/instructions/ambiental-media/jor-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ambiental-media/jor-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.
<a href="https://agentmods.dev/instructions/ambiental-media/jor-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ambiental-media/jor-mcp/agents-md.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 | $0.02515 | $0.02515 |
| Opus 5 | $0.01257 | $0.01257 |
| Sonnet 5 | $0.00503 | $0.00503 |
| Haiku 4.5 | $0.00251 | $0.00251 |
Grade A, and why
jor-mcp AGENTS.md scanned grade A with 1 finding 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 9d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **Subprocesses:** Never use `os.system` or `subprocess.run(..., shell=True)` with unvalidated input to prevent shell injection vulnerabilities. How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Instructions for jor-mcp
Welcome, AI Agent. This AGENTS.md file defines the standard operating procedures, commands, and code style guidelines for the jor-mcp project. You must strictly adhere to these instructions to ensure high-quality, safe, and consistent contributions to this repository.
Project Context
- Name: jor-mcp
- Purpose: A Model Context Protocol (MCP) server for Ambiental Media, searching journalism content across WordPress and GitHub.
- Language: Python >= 3.12
- Core Libraries:
fastmcp,uvicorn,httpx(async),pyjwt,opentelemetry - Dependency Manager:
uv
Prerequisite: Development Standards
Before making any changes, you must read and adhere to the rules defined in CONTRIBUTING.md. This includes:
- Language Constraint: All technical communication (commit messages, PR descriptions, code comments, variable names, and documentation) MUST be in English. (The only exception is the
@mcp.tool()description parameter, which must remain in Portuguese). - Using
uvfor all dependency management and task execution. - Enforcing strict typing, linting (
ruff), and formatting. - Ensuring all new code maintains the 90% test coverage minimum.
- Validation: After writing or modifying code, use the
make checkcommand to run all linters, formatters, type checkers, and tests at once. Do not propose a Pull Request or consider a task finished untilmake checkpasses completely. - Documentation Sync: For every proposed change, you MUST review and update the
docs/directory to ensure it accurately reflects the new code, new environment variables, or new architecture. Never submit code changes without checking if the technical, deployment, or usage documentation needs updating.
Code Style, Conventions & Python Best Practices
AI Agents operating in this repository must strictly adhere to the following community best practices and modern Python 3.12+ paradigms.
1. File Structure, Imports & Project Layout
- PEP 8: Style Guide for Python Code (The foundational aesthetic standard).
- PEP 20: The Zen of Python (Guiding philosophy for clean code).
- PEP 695: Type Parameter Syntax (Modern 3.12+ generics and type aliases).
- The "Src Layout": All source code must reside in
src/. This forces tests to run against the installed package rather than the local folder, preventing accidental import leaks. - Absolute Imports: Always use absolute imports anchored at
src. Do not use relative imports (likefrom .config import ...).- Good:
from src.config import GITHUB_TOKEN - Bad:
from .config import GITHUB_TOKEN
- Good:
- Import Ordering: Imports must be grouped and sorted. Run
uv run ruff check . --fixto organize them automatically after writing code. - Dependency Management: Use
uvas the single source of truth for dependency management. - Tooling: Use
Rufffor all linting and formatting (rules: E, F, I, UP, S, B), replacing Flake8, Isort, and Black.
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.
- 9d ago First seen · 126 lines · 2,515 tokens per session scan A 4e0efbf90e17
jor-mcp AGENTS.md is an instructions file published in the GitHub repository ambiental-media/jor-mcp (4 stars, last pushed 9d ago), licensed Apache-2.0. It adds 2,515 tokens to every session, about $0.0126 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.