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/hamzaamjad/cursor-rules/003-stepwise-autonomygit clone --depth 1 https://github.com/hamzaamjad/cursor-rulesWhat 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 | $0.01682 | $0.01682 |
| Opus 5 | $0.00841 | $0.00841 |
| Sonnet 5 | $0.00336 | $0.00336 |
| Haiku 4.5 | $0.00168 | $0.00168 |
Grade A, and why
003-stepwise-autonomy 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stepwise Autonomy Protocol
Purpose
To guide AI assistants in reliably executing complex tasks by breaking them down into verifiable steps and using tools judiciously to reduce uncertainty. This protocol integrates Tree of Thoughts reasoning for complex scenarios and emphasizes systematic verification at each execution stage.
Core Protocol
Task Complexity Assessment
Classify each task into one of three complexity levels to determine appropriate protocol rigor:
Simple Tasks: Single-step operations with predictable outcomes. Apply streamlined protocol with minimal planning and basic verification.
Moderate Tasks: Multi-step operations with well-defined boundaries. Apply standard protocol with structured planning and systematic verification.
Complex Tasks: Operations requiring significant planning or cross-system coordination. Apply enhanced protocol with Tree of Thoughts exploration and comprehensive verification.
For detailed assessment criteria and examples, see @Notepad:notepads/000-core/stepwise-autonomy/complexity-assessment-guide.md.
Execution Requirements
Each task execution must satisfy these core requirements regardless of complexity level:
Task Decomposition: Break down the task into discrete, verifiable steps. For complex tasks, generate multiple solution paths using Tree of Thoughts methodology, evaluating each path's promise before commitment.
Resource Verification: Confirm availability of required libraries, configuration files, APIs, and services before execution begins. Verify structural integrity of artifact collections when working with multi-file components.
Scope Confirmation: Explicitly confirm performance targets, output format preferences, and constraint specifications with quantitative metrics where possible.
Progressive Verification: Confirm success of each step before proceeding. Complex tasks require verification checkpoints at predetermined milestones.
Execution Protocol
The stepwise autonomy protocol follows a systematic approach tailored to task complexity:
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 · 141 lines · 1,682 tokens per session scan A cf752a0317e5
003-stepwise-autonomy is a cursor rule published in the GitHub repository hamzaamjad/cursor-rules (2 stars, last pushed 1y ago), licensed MIT. It adds 1,682 tokens to every session, about $0.0084 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
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.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.