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/moclam1905/cocktailrecipes/task-breakdown-alwaysgit clone --depth 1 https://github.com/moclam1905/CocktailRecipesWrote 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/moclam1905/cocktailrecipes/task-breakdown-always)<a href="https://agentmods.dev/rules/moclam1905/cocktailrecipes/task-breakdown-always"><img src="https://agentmods.dev/badge/rules/moclam1905/cocktailrecipes/task-breakdown-always.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 | $0.00393 | $0.00393 |
| Opus 5 | $0.00197 | $0.00197 |
| Sonnet 5 | $0.00079 | $0.00079 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade A, and why
task-breakdown-always 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 3d 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.
What it actually says
Task Breakdown Rule
Critical Rules
- Identify high-level bullet points in tasks.md that lack subtasks
- Break down each high-level task into 3-5 specific, actionable subtasks
- Add effort estimates (in hours) for each subtask in parentheses
- Ensure subtasks align with the architectural decisions in techContext.md
- Maintain the existing markdown format with proper indentation
- Do not modify completed tasks (marked with [x])
- Update tasks.md in-place with the new breakdown
- Respect dependencies between tasks (complete prerequisite tasks first)
- Use consistent terminology across all subtasks
Examples
After:
## Phase 1: Project Setup & Architecture
- [x] Create initial project structure
- [ ] Set up project architecture (MVVM)
- [ ] Create data, domain, and presentation layer packages (1h)
- [ ] Implement base ViewModel class with error handling (2h)
- [ ] Set up dependency injection structure (2h)
- [ ] Create repository interfaces (1h)
After:
## Phase 1: Project Setup & Architecture
- [ ] Implement architecture
- [ ] Do the MVVM thing
- [ ] Create some files
The breakdown is too vague and doesn't provide specific, actionable subtasks with effort estimates.
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.
- 3d ago First seen · 60 lines · 393 tokens per session scan A deb06604aa9e
task-breakdown-always is a cursor rule published in the GitHub repository moclam1905/CocktailRecipes (1 stars, last pushed 1y ago), licensed MIT. It adds 393 tokens to every session, about $0.0020 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.
Other cursor rules, from other repositories
github-repo-triage
Triage and maintain GitHub repos — issues, PRs, cherry-picks, releases, publishing.
ai-dev-os-ticket
Generates a ticket (local file or GitHub Issue) with implementation summary and checklist candidates derived from AI Dev OS guidelines. Used to create structured implementation tasks.
12-new-project
Workflow for starting a new app from this template - rebranding, identity, cleanup and first feature.
13-updating-project
Workflow for updating an existing project - dependency and SDK upgrades, migrations, refactors, bug fixes.
agent-workflow-orchestration
Mandatory PM-orchestrated subagent workflow — main agent is manager, no separate PM subagent.
android-project
Core behavior rules for AI agents working on this Android project.