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.
git clone --depth 1 https://github.com/Intrafere/MOTO-Autonomous-ASIWrote 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/intrafere/moto-autonomous-asi/part-3-autonomous-research-mode)<a href="https://agentmods.dev/rules/intrafere/moto-autonomous-asi/part-3-autonomous-research-mode"><img src="https://agentmods.dev/badge/rules/intrafere/moto-autonomous-asi/part-3-autonomous-research-mode/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/intrafere/moto-autonomous-asi/part-3-autonomous-research-mode"><img src="https://agentmods.dev/badge/rules/intrafere/moto-autonomous-asi/part-3-autonomous-research-mode.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 | $0.29981 | $0.29981 |
| Opus 5 | $0.14991 | $0.14991 |
| Sonnet 5 | $0.05996 | $0.05996 |
| Haiku 4.5 | $0.02998 | $0.02998 |
Grade A, and why
part-3-autonomous-research-mode 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 7d 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 — 1,751 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Part 3 (Adding an Autonomous-Controlling Tier in Hierarchy Over Part 1 and 2) - Autonomous Research Mode Design Specification
Overview
The Autonomous Research Mode is Part 3 of MOTO's self-directing three-tier research system. It autonomously generates brainstorm topics, builds knowledge databases, produces rigorous solution-oriented research papers or reports, and can synthesize a final answer centered on the user's high-level objective. Mathematics and formal proof remain first-class when relevant.
Example User Prompt: "Solve the Langlands Bridge problem" or "Advance understanding of the Riemann Hypothesis"
Key Difference from Manual Modes:
- Part 1 (Aggregator) requires user-provided topic prompts
- Part 2 (Compiler) requires user-directed paper compilation prompts
- Part 3 (Autonomous Research) self-directs topic selection, brainstorming, and paper generation
Three-Tier Architecture:
- Tier 1: Brainstorm aggregation databases (solution concept, mechanism, evidence, algorithm, and mathematical exploration)
- Tier 2: Finished rigorous research papers or solution reports (compiled from brainstorm databases)
- Tier 3: Final answer synthesis (short-form answer or long-form volume from Tier 2 papers)
Design Philosophy
Self-Directing Research: The AI autonomously identifies the most valuable research avenues based on the high-level goal prompt.
Domain-General Strategy: Ordinary topic exploration/selection, completion review, reference selection, title selection, and continuation aggressively pursue the strongest solution path for the exact objective using domain- and claim-appropriate rigor. When Mathematical Proofs is allowed, mathematics and formal proof remain first-class when useful under the eager startup proof-framing emphasis; when disabled in Allowed Outputs, that framing is skipped. Positive proof framing is emphasis, not a hard mathematical admission requirement for every ordinary contribution.
Basin Exploration: Each brainstorm topic represents a "basin" of related solution concepts, mechanisms, evidence, algorithms, designs, or mathematical structures. The system explores each basin until sufficiently complete, then generates a paper.
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.
- 7d ago Changed · +28 tokens per session 7f8cfa226f0c
- 11d ago First seen · 1,751 lines · 29,953 tokens per session scan A 484fbcc389ef
part-3-autonomous-research-mode is a cursor rule published in the GitHub repository Intrafere/MOTO-Autonomous-ASI (82 stars, last pushed 7d ago), licensed MIT. It adds 29,981 tokens to every session, about $0.1499 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
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.
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.