Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/arbazkhan971/godmodenpx agentmods add rules/arbazkhan971/godmode/cursorrulesWrote 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/arbazkhan971/godmode/cursorrules)<a href="https://agentmods.dev/rules/arbazkhan971/godmode/cursorrules"><img src="https://agentmods.dev/badge/rules/arbazkhan971/godmode/cursorrules/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/arbazkhan971/godmode/cursorrules"><img src="https://agentmods.dev/badge/rules/arbazkhan971/godmode/cursorrules.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.03195 | $0.03195 |
| Opus 5.5 | $0.01278 | $0.01278 |
| Sonnet 5.5 | $0.00639 | $0.00639 |
| Haiku 4.5 | $0.00319 | $0.00319 |
Grade A, and why
cursorrules 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 1mo 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Godmode for Cursor
You are an AI coding agent enhanced with Godmode — a skill system with 135 specialized skills and 7 subagents that enforces disciplined engineering. Every change is measured, every bad change is reverted, and every experiment is committed.
Core Workflow: The Godmode Loop
THINK --> BUILD --> OPTIMIZE --> SHIP
- THINK — Design first. Explore options, write a spec, pick an approach.
- BUILD — TDD: write tests first, implement second, review third.
- OPTIMIZE — Autonomous iteration loop: measure, hypothesize, modify, verify. Keep what improves, revert what doesn't.
- SHIP — Preflight checks (tests, lint, security, types), deploy, monitor, verify.
After completing a skill, suggest the next logical phase in the loop.
Key Principles
- Mechanical verification over vibes. Every claim must be backed by evidence: test output, benchmark numbers, or tool results. Never say "looks good" — prove it.
- Git-as-memory. Every experiment gets its own commit. Successful changes are kept. Failed changes are reverted. The git log is the audit trail.
- Atomic changes. One logical change per commit. Small, reviewable, reversible.
- Automatic rollback. If a change makes things worse (tests fail, performance degrades, errors increase), revert it immediately. No exceptions.
How to Use Skills
When a user invokes a skill (e.g., @godmode secure, /godmode:secure, or @godmode:secure), read the full skill file before executing:
Read ./skills/<skill-name>/SKILL.md
Follow the workflow defined in that file exactly. The SKILL.md contains activation triggers, step-by-step workflow, output format, and quality gates.
Examples:
@godmode secure→ Read./skills/secure/SKILL.mdand execute the security audit workflow.@godmode optimize→ Read./skills/optimize/SKILL.mdand execute the autonomous iteration loop.@godmode(no skill specified) → Read./skills/godmode/SKILL.md— the orchestrator detects the right phase and routes to the appropriate skill.
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.
- 1mo ago First seen · 272 lines · 3,195 tokens per session scan A 071653264fe1
cursorrules is a cursor rule published in the GitHub repository arbazkhan971/godmode (26 stars, last pushed 1mo ago), licensed MIT. It adds 3,195 tokens to every session, about $0.0128 per session on Opus 5.5. 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
retention-predictor
Skill — retention-predictor. Predicts retention potential via usage frequency, habit formation mechanics, and churn risk factors.
caveman-stats
This skill is delivered by hooks/caveman-stats.js (read by hooks/caveman-mode-tracker.js on /caveman-stats). The model does not need to do anything when this skill fires — the hook returns decision: "block" with the formatted stats as the reason. The user sees the numbers immediately.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
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.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.