simplenote-mcp-server AGENTS.md

simplenote-mcp-server AGENTS.md is an instructions file for Codex, OpenCode from docdyhr/simplenote-mcp-server. It costs 2,244 tokens per session, scanned A, original, MIT.

Project instructions for simplenote-mcp-server, a Python server that connects Simplenote to AI clients such as Claude Desktop. They describe setup commands, the project structure, tests, code checks, and evaluations.

In plain words
What is it for?
Use them when installing dependencies, running fast or legacy tests, checking formatting and types, scanning for security issues, or running the project's evaluation scripts.
Why use it?
They give a coding agent the repository-specific rules needed to work safely and consistently. They also clarify that the two test suites must be run separately and which commands to use.

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/docdyhr/simplenote-mcp-server/agents-md
Clone the repo
git clone --depth 1 https://github.com/docdyhr/simplenote-mcp-server

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 simplenote-mcp-server AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/docdyhr/simplenote-mcp-server/agents-md.svg)](https://agentmods.dev/instructions/docdyhr/simplenote-mcp-server/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/docdyhr/simplenote-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/docdyhr/simplenote-mcp-server/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,244 This file is loaded in full into every session.
When invoked 2,244 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 $0.02244 $0.02244
Opus 5 $0.01122 $0.01122
Sonnet 5 $0.00449 $0.00449
Haiku 4.5 $0.00224 $0.00224

Measured 5d ago against content hash b1b17638ef6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

simplenote-mcp-server 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 · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

simplenote-mcp-server

MCP server connecting Simplenote to Claude Desktop and other MCP clients. Python ≥3.10, package root simplenote_mcp/.

Commands

# Setup
pip install -e ".[dev,test,all]"
pre-commit install

# Tests — two independent trees, run separately (see tests/AGENTS.md and simplenote_mcp/tests/AGENTS.md for why)
make test-fast      # SIMPLENOTE_OFFLINE_MODE=true .venv/bin/pytest tests/ -x -q --timeout=30
make test-legacy    # SIMPLENOTE_OFFLINE_MODE=true .venv/bin/pytest simplenote_mcp/tests/ -q --timeout=30 --no-cov
make test           # both, via .venv/bin/pytest -q (root testpaths = tests/ only; legacy run separately in CI)

# Quality
ruff check .
ruff format .
mypy simplenote_mcp
bandit -c pyproject.toml -r simplenote_mcp   # always pass -c; bare invocation misapplies exclude_dirs

# Evaluations (npm devDependency tree, never shipped — see package.json)
npm install && npm run eval:smoke   # eval:basic, eval:comprehensive, eval:all also available

Always invoke .venv/bin/pytest / .venv/bin/ruff / .venv/bin/mypy / .venv/bin/bandit explicitly, or prefix with source .venv/bin/activate && in the same shell call — each Bash invocation is a fresh shell, so a prior activate does not persist and bare commands silently resolve through the pyenv shim to the global environment instead of .venv.

Architecture

simplenote_mcp/
├── server/            # MCP protocol handlers, tool registry, cache, security — see server/AGENTS.md
│   ├── search/         # Query parser + boolean/fuzzy/date search engine — see server/search/AGENTS.md
│   └── monitoring/      # Metrics collection + alerting thresholds — see server/monitoring/AGENTS.md
├── scripts/            # Runtime diagnostics shipped with the package — see simplenote_mcp/scripts/AGENTS.md
├── tests/               # Legacy pytest tree, separate invocation — see simplenote_mcp/tests/AGENTS.md
└── __main__.py         # Entry point (module execution)
tests/                  # Primary CI-wired pytest tree — see tests/AGENTS.md
scripts/                # CI/quality/release tooling — see scripts/AGENTS.md
helm/                   # Helm chart — see helm/AGENTS.md
.github/workflows/      # CI/CD pipelines — see .github/workflows/AGENTS.md
docs/, evals/           # Reference docs and mcp-evals suites; no durable local contracts of their own

Read the full file on GitHub · 171 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. 5d ago First seen · 171 lines · 2,244 tokens per session scan A b1b17638ef6b

Subscribe to this mod's changes

simplenote-mcp-server AGENTS.md is an instructions file published in the GitHub repository docdyhr/simplenote-mcp-server (19 stars, last pushed 2d ago), licensed MIT. It adds 2,244 tokens to every session, about $0.0112 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 2026-08-30.