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-2-compiler-tool-design-specification)<a href="https://agentmods.dev/rules/intrafere/moto-autonomous-asi/part-2-compiler-tool-design-specification"><img src="https://agentmods.dev/badge/rules/intrafere/moto-autonomous-asi/part-2-compiler-tool-design-specification/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-2-compiler-tool-design-specification"><img src="https://agentmods.dev/badge/rules/intrafere/moto-autonomous-asi/part-2-compiler-tool-design-specification.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 | $0.06561 | $0.06561 |
| Opus 5 | $0.03281 | $0.03281 |
| Sonnet 5 | $0.01312 | $0.01312 |
| Haiku 4.5 | $0.00656 | $0.00656 |
Grade A, and why
part-2-compiler-tool-design-specification 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 10d 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Main Architecture layout/design of the distillation/compiler portion of the two-part aggregation-distillation LLM workflow.
Workflow Compiler Note
Compiler runs independently from aggregator (manual start via API only). Strict Markov-chain: one active compiler role submits at a time, waits for validation/result handling before resuming. Only 1 submission in queue at a time.
Progressive Solution Path
Compiler continues the one durable manual-run Progressive Solution Path owned by Aggregator; compiler paper acceptances never activate it or create a second owner. Once the manual run has five accepted brainstorm submissions and a Main Submitter 1-approved revision, the bounded canonical plan is optional advisory direct context for relevant solving and semantic-validator prompts and may be ignored for a better route. Only existing Compiler semantic LLM validators may optionally propose material route/goal/evidence/meaningful-step updates in their normal JSON; this extension is parsed separately and cannot invalidate or change the paper decision. Exact-string checks, marker repair, Lean/tool/integrity results, submitters, and other deterministic checks never originate proposals. Dedicated exact-Main-Submitter-1 review is asynchronous, serial, and transactional; Stop/Start preserves state, while manual Clear deletes/resets the active path separately from proof-run archival.
After backend restart, manual Compiler reconstructs that persisted manager from the durable Aggregator prompt/run identity and the latest available Main Submitter 1 configuration. A manual clear deletes only the active manual run's solution-path state.
Compile/Distillation Tool Outline
Reads aggregator database + user prompt, distills into a single coherent paper. Runtime roles are Writing Submitter, Rigor & Proofs Submitter (legacy high_param_* fields), Validator, and optional Assistant. Main construction/rigor remains sequential; post-body critique generation is performed by Rigor & Proofs while critique validation/cleanup remain Validator-owned.
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.
- 10d ago First seen · 278 lines · 6,561 tokens per session scan A 942dcec85be4
part-2-compiler-tool-design-specification is a cursor rule published in the GitHub repository Intrafere/MOTO-Autonomous-ASI (83 stars, last pushed 6d ago), licensed MIT. It adds 6,561 tokens to every session, about $0.0328 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.