Productive-Simple-MCP AGENTS.md

Productive-Simple-MCP AGENTS.md is an instructions file for Codex, OpenCode from druellan/Productive-Simple-MCP. It costs 421 tokens per session, scanned A, original, MIT.

A set of repository instructions for building and maintaining a Python service that connects to the Productive API. It documents project files, coding rules, commands, and checks.

In plain words
What is it for?
Use it when working on the service's server, API client, configuration, helpers, output formats, or verification checks.
Why use it?
It gives an agent the local rules needed to make compatible changes and avoid common problems such as blocking network calls or exposed credentials.

Instructions file for CodexOpenCode

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 instructions/druellan/productive-simple-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/druellan/Productive-Simple-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 Productive-Simple-MCP AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/druellan/productive-simple-mcp/agents-md.svg)](https://agentmods.dev/instructions/druellan/productive-simple-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/druellan/productive-simple-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/druellan/productive-simple-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 421 This file is loaded in full into every session.
When invoked 421 The same file — it is already loaded in full.
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 5.1 $0.00421 $0.00421
Opus 5 $0.00211 $0.00211
Sonnet 5 $0.00084 $0.00084
Haiku 4.5 $0.00042 $0.00042

Measured 5d ago against content hash dd2a280aa4b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

Productive-Simple-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.

AGENTS.md · 58 lines

What it actually says

Do

  • Use uv for Python package management
  • Follow Python 3.10+ syntax and type hints
  • Use async/await for I/O operations
  • Use TOON output for efficiency

Don't

  • Don't expose API keys or secrets
  • Don't use sync HTTP calls
  • Don't hardcode credentials

Quick Commands

  • Install dependencies: uv sync
  • Run server: python server.py
  • Check syntax: python -m py_compile server.py tools.py config.py productive_client.py utils.py

Repo Map

  • server.py: FastMCP server setup and tool definitions
  • tools.py: Implementation of Productive API calls
  • config.py: Environment variable configuration
  • productive_client.py: HTTP client for Productive API
  • utils.py: Helper functions
  • pyproject.toml: Project metadata and dependencies

Working Rules

  • Use async/await for all I/O operations
  • Validate configuration on startup
  • Strip HTML and optimize output for LLMs
  • Include webapp URLs in responses for direct access
  • Handle errors gracefully without exposing internals

Verification Steps

  • Run python -m file.py and confirm no startup errors
  • Check that all tools are registered in MCP
  • Verify TOON/JSON output formats work
  • Smoke test the packaged entrypoint: set PRODUCTIVE_API_KEY and PRODUCTIVE_ORGANIZATION, then run uv run productive-mcp and confirm the server starts without TypeError: 'FastMCP' object is not callable
  • Ask the user for testing instructions when necessary

Security Boundaries

  • API tokens loaded from environment variables only
  • No logging of sensitive data
  • HTTPS enforced for all API requests
  • Error messages don't leak credentials

PR/Change Checklist

  • Server starts without errors
  • No secrets or credentials committed
  • Type hints added for new functions
  • Output optimized for LLM consumption
  • README updated if tools changed
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. 5d ago First seen · 58 lines · 421 tokens per session scan A dd2a280aa4b9

Subscribe to this mod's changes

Productive-Simple-MCP AGENTS.md is an instructions file published in the GitHub repository druellan/Productive-Simple-MCP (0 stars, last pushed 7d ago), licensed MIT. It adds 421 tokens to every session, about $0.0021 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.