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.
git clone --depth 1 https://github.com/neuromechanist/research-skillsWrote 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/rules/neuromechanist/research-skills/taskmaster_reference)<a href="https://agentmods.dev/rules/neuromechanist/research-skills/taskmaster_reference"><img src="https://agentmods.dev/badge/rules/neuromechanist/research-skills/taskmaster_reference.svg" alt="Measured on agentmods" 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 | $0.04309 | $0.04309 |
| Opus 5 | $0.02155 | $0.02155 |
| Sonnet 5 | $0.00862 | $0.00862 |
| Haiku 4.5 | $0.00431 | $0.00431 |
Grade A, and why
taskmaster_reference 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Taskmaster Tool & Command Reference
This document provides a detailed reference for interacting with Taskmaster, covering both the recommended MCP tools (for integrations like Cursor) and the corresponding task-master CLI commands (for direct user interaction or fallback).
Note: For interacting with Taskmaster programmatically or via integrated tools, using the MCP tools is strongly recommended due to better performance, structured data, and error handling. The CLI commands serve as a user-friendly alternative and fallback. (Implementation details for MCP/CLI are assumed to be internal to Taskmaster).
Important: Several MCP tools involve AI processing and are long-running operations that may take up to a minute to complete. When using these tools, always inform users that the operation is in progress and to wait patiently for results. The AI-powered tools include: parse_prd, analyze_project_complexity, update_subtask, update_task, update, expand_all, expand_task, and add_task.
Initialization & Setup
1. Initialize Project (init)
- MCP Tool:
initialize_project - CLI Command:
task-master init [options] - Description: Set up the basic Taskmaster file structure and configuration in the current directory for a new project.
- Key CLI Options:
--name <n>: Set project name.--description <text>: Set project description.--version <version>: Set initial version.-y, --yes: Initialize with defaults, no prompts.
- Key MCP Parameters/Options:
projectRoot: Required. Absolute path to the project directory.projectName: Project name (CLI:--name).projectDescription: Project description (CLI:--description).projectVersion: Initial version (CLI:--version).skipInstall: Skip dependency install (CLI:--skip-install).addAliases: Add shell aliases (CLI:--aliases).yes: Skip prompts (CLI:-y, --yes). Must be true for MCP.
- Usage: Run once at the start of a new project.
- Important: After
init, runparse_prdto generate initial tasks from a requirements document.
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.
- 4d ago First seen · 332 lines · 4,309 tokens per session scan A 855861112b4a
taskmaster_reference is a cursor rule published in the GitHub repository neuromechanist/research-skills (45 stars, last pushed 5d ago), licensed BSD-3-Clause. It adds 4,309 tokens to every session, about $0.0215 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 2026-09-04.
Other cursor rules, from other repositories
team-brain
Team Brain sync mode — one start per ticket, then live merge-safe crew memory. Always-on when .team-brain exists or work mentions an initiative/Jira key.
3-process-task-list
Guidelines for managing task lists in markdown files to track progress on completing a PRD.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.