atomic-task-planning

A set of rules for breaking development work into the smallest clear tasks and completing them one at a time. It requires a task list before work starts and pauses after each task is finished.

In plain words
What is it for?
Use it to structure coding and other project work into small steps with clear outcomes.
Why use it?
It reduces confusion in larger jobs by making each piece of work independently checkable.

Cursor rule

Install

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.

agentmods
npx agentmods add rules/barisercan/cursorrules/atomic-task-planning
Clone the repo
git clone --depth 1 https://github.com/barisercan/cursorrules
Per session 783 This file is loaded in full into every session.
When invoked 783 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce 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

Measured yesterday against content hash 5f201ef70aa6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

atomic-task-planning.mdc · 112 lines

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:

    1. 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
    2. 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
    3. 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
    4. 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"
    5. 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:

    1. Receive request
    2. Break into atomic tasks
    3. Present task list for approval
    4. Execute task 1
    5. Stop and confirm completion
    6. Execute task 2
    7. Repeat until all tasks done

examples:

  • input: | User: "Add user authentication"

    Correct approach:

    "I'll break this into atomic tasks:

    1. Create User model
    2. Add password hashing method
    3. Create login endpoint
    4. Add authentication middleware
    5. 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:

    1. Identify the calculation error
    2. Write test that reproduces bug
    3. Fix the specific calculation line
    4. 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"]

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.

  1. yesterday First seen · 112 lines · 783 tokens per session scan A 5f201ef70aa6

Subscribe to this mod's changes

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.