What is Super-Productivity-MCP AGENTS.md?

Development instructions for a Super Productivity integration made of a TypeScript server and a JavaScript plugin that exchange files as messages.

Use them to build, test, type-check, lint, and debug tools that read or modify Super Productivity tasks, projects, and tags.

They document the project structure, build and test commands, and the file-based communication details needed to change the integration safely.

How b0x42/Super-Productivity-MCP configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to b0x42/Super-Productivity-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/b0x42/Super-Productivity-MCP/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/b0x42/Super-Productivity-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/b0x42/super-productivity-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/b0x42/super-productivity-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/b0x42/super-productivity-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/b0x42/super-productivity-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/b0x42/super-productivity-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/b0x42/super-productivity-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 867 This file is loaded in full into every session.

When invoked 867 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.

Model	Per session	Once invoked
Fable 5.1	$0.00867	$0.00867
Opus 5.5	$0.00347	$0.00347
Sonnet 5.5	$0.00173	$0.00173
Haiku 4.5	$0.00087	$0.00087

Measured 1mo ago against content hash 7e25a9d05945, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Super-Productivity-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 1mo 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 · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

CLAUDE.md is a symlink to this file for Claude Code compatibility.

Commands

npm run build        # compile MCP server (tsup) + zip plugin → dist/plugin.zip
npm run build:server # tsup only — dist/index.js
npm run build:plugin # inline the pane into index.html, then zip → dist/plugin.zip
npm run dev          # watch mode
npm test             # vitest run
npm run test:watch   # vitest watch
npm run typecheck    # tsc --noEmit (use this, not npx tsc — tsc not in PATH)
npm run lint         # eslint src/

A Makefile wraps these; the npm scripts stay the source of truth (CI and prepublishOnly call them directly). What it adds is dependency tracking — dist/index.js and dist/plugin.zip are real file targets, so an unchanged tree rebuilds nothing.

make                 # build both artifacts
make verify          # typecheck + lint + test — the pre-commit gate
make mcp-add         # register with Claude Code (SCOPE=local to override)
make mcp-remove
make clean

Architecture

Two components communicating via file-based IPC:

MCP server (src/) — TypeScript, built with tsup
SP plugin (plugin/) — JavaScript + HTML, loaded into Super Productivity

Plugin writes responses to plugin_responses/, server reads. Server writes commands to plugin_commands/, plugin polls.

src/
  ipc/
    command-sender.ts   # sendCommand() — writes command file, polls for response
    directories.ts      # platform-aware IPC dir discovery (macOS/Linux/Windows/snap)
    types.ts            # shared types (TaskFilters, Command, etc.)
  tools/
    tasks.ts            # get_tasks, create_task, update_task, reorder_tasks, …
    projects.ts         # get_projects, create_project, update_project
    tags.ts             # get_tags, create_tag, update_tag
    habits.ts           # get_habits, create_habit, update_habit, check_habit, set_habit_value, delete_habit
    habit-streak.ts     # streak computation, ported from SP's own algorithm (pure, unit-tested)
    notifications.ts    # show_notification
    diagnostics.ts      # debug tool
    result.ts           # okResult() / errorResult() helpers
  server.ts             # registers all tools
  index.ts              # entry point
plugin/
  plugin.js             # SP plugin — handles all MCP commands, calls PluginAPI
tests/
  unit/tools/           # vitest unit tests

Read the full file on GitHub · 91 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.

1mo ago Changed · +15 lines · +186 tokens per session 7e25a9d05945
2mo ago First seen · 76 lines · 681 tokens per session scan A f205eb1a46a3

Subscribe to this mod's changes

Super-Productivity-MCP AGENTS.md is an instructions file published in the GitHub repository b0x42/Super-Productivity-MCP (131 stars, last pushed 5d ago), licensed MIT. It adds 867 tokens to every session, about $0.0035 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 2026-08-30.

Building agents

Super-Productivity-MCP AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Super-Productivity-MCP AGENTS.mdb0x42/Super-Productivity-MCP	Instructions file	131	5d ago	MIT	A	867	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

Super-Productivity-MCP: Instructions file for Codex