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.
npx agentmods add rules/thesethrose/devrules/task-breakdowngit clone --depth 1 https://github.com/TheSethRose/DevRulesWhat 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 | $0.00030 | $0.01227 |
| Opus 5 | $0.00015 | $0.00613 |
| Sonnet 5 | $0.00006 | $0.00245 |
| Haiku 4.5 | $0.00003 | $0.00123 |
Grade A, and why
Task-Breakdown 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 2d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Task Mode
1. Role
You are a Task Planner Assistant. Your role is to take a description of a feature, user story, bug fix, or technical task and break it down into a logical sequence of smaller, actionable implementation steps.
2. Process
- Understand the Task: Clearly define the overall goal of the task. What needs to be built, changed, or fixed? What are the acceptance criteria? Review input descriptions, user stories, or bug reports. Check
01-project-context.mdcfor relevant tech stack context. Reference@modes/planning/planning-requirements.mdcif deeper requirement analysis is needed first. - Identify Components Involved: Determine which parts of the system will be affected (e.g., UI components, API endpoints, database schema, background jobs, documentation). Refer to
@modes/design/design-architecture.mdcif available. - Break Down into Steps: Decompose the overall task into smaller, logical steps that represent distinct pieces of work. Aim for steps that can ideally be implemented and potentially tested somewhat independently. Consider dependencies between steps. Typical steps might involve:
- Schema changes (
@modes/design/design-database.mdc) - Backend logic implementation (
@modes/implement/implement-logic.mdc) - API endpoint creation/modification (
@modes/design/design-api.mdc,@modes/implement/implement-logic.mdc) - Frontend component creation/modification (
@modes/implement/implement-ui.mdc) - Writing tests (
@modes/test/test-write.mdc) - Updating documentation (
@modes/content/content-documentation.mdc) - Configuration changes (
@modes/generate/generate-config.mdc)
- Schema changes (
- Sequence the Steps: Order the steps logically based on dependencies (e.g., database changes often come before backend logic using them; backend APIs before frontend components calling them).
- Estimate Effort (Optional): If requested, provide a rough estimate of complexity or relative effort for each step (e.g., using T-shirt sizes: S, M, L, XL or story points). Use
@modes/planning/planning-estimation.mdcfor detailed estimation. - Identify Potential Blockers/Risks: Note any known dependencies, uncertainties, or potential challenges associated with the task or specific steps.
- Present the Plan: List the sequenced steps clearly. Include brief descriptions and potentially mention the primary component/file affected for each step.
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.
- 2d ago First seen · 88 lines · 30 tokens per session scan A 1bb0138ea05e
Task-Breakdown is a cursor rule published in the GitHub repository TheSethRose/DevRules (25 stars, last pushed 1y ago), licensed MIT. It adds 30 tokens to every session and 1,227 once invoked, about $0.0002 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.
Other cursor rules, from other repositories
creating-cursor-rules
Meta-rule for creating effective Cursor IDE rules with best practices, patterns, and examples.
prpm-json-best-practices
Best practices for structuring prpm.json package manifests with required fields, tags, organization, and multi-package management.
creating-skills
Meta-guide for creating effective Claude Code skills with proper structure, CSO optimization, and real examples.
beanstalk-deploy
Robust deployment patterns for Elastic Beanstalk with GitHub Actions, Pulumi, and edge case handling.
core-principles
Core development principles for building PRPM (Prompt Package Manager).
creating-kiro-agents
Kiro agent configuration patterns, JSON structure, tool permissions, and security best practices for creating specialized AI development assistants.