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/barisercan/cursorrules/atomic-task-planninggit clone --depth 1 https://github.com/barisercan/cursorrulesWhat 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 | $0.00783 | $0.00783 |
| Opus 5 | $0.00392 | $0.00392 |
| Sonnet 5 | $0.00157 | $0.00157 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
atomic-task-planning 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 yesterday.
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
description: Break down all work into smallest possible atomic tasks and execute them sequentially globs: "**/*" alwaysApply: true
Atomic Task Planning
Divide every job into the smallest possible atomic tasks and execute them one by one.
actions:
-
type: enforce message: | ATOMIC TASK PLANNING PROTOCOL
MANDATORY WORKFLOW:
-
PLANNING PHASE REQUIRED:
- NEVER start work without atomic task breakdown
- Divide ALL jobs into smallest possible tasks
- Tasks can be as small as writing a single method
- Tasks can be as small as renaming a variable
- Present complete task list before starting
-
ATOMIC TASK CRITERIA:
- Each task must be independently completable
- Should take minimal time to execute
- Must have clear, measurable outcome
- Cannot be broken down further meaningfully
-
EXECUTION RULES:
- Execute tasks ONE BY ONE only
- Complete current task before starting next
- Never work on multiple tasks simultaneously
- Stop after each task completion
-
TASK EXAMPLES:
- "Write getUserById method"
- "Add email validation"
- "Rename variable 'data' to 'userData'"
- "Add error handling to login function"
- "Update import statement"
- "Add single test case for edge condition"
-
NO TASK TOO SMALL:
- Prefer smaller tasks over larger ones
- When in doubt, break it down further
- Single line changes are valid tasks
- Micro-improvements are encouraged
WORKFLOW:
- Receive request
- Break into atomic tasks
- Present task list for approval
- Execute task 1
- Stop and confirm completion
- Execute task 2
- Repeat until all tasks done
-
examples:
-
input: | User: "Add user authentication"
Correct approach:
"I'll break this into atomic tasks:
- Create User model
- Add password hashing method
- Create login endpoint
- Add authentication middleware
- Add logout functionality
Should I proceed with task 1?" output: "Proper atomic task breakdown with sequential execution"
-
input: | User: "Fix the bug in calculation"
Correct approach:
"I'll break this into atomic tasks:
- Identify the calculation error
- Write test that reproduces bug
- Fix the specific calculation line
- Verify test passes
Should I start with task 1?" output: "Bug fix broken into atomic steps"
metadata: priority: high version: 1.0 enforcement: strict dependencies: ["minimal-changes-policy", "test-driven-development"]
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.
- yesterday First seen · 112 lines · 783 tokens per session scan A 5f201ef70aa6
atomic-task-planning is a cursor rule published in the GitHub repository barisercan/cursorrules (35 stars, last pushed 1y ago), licensed MIT. It adds 783 tokens to every session, about $0.0039 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
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.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.