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/alieismy/codex-three-layer-deliveryWrote 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/alieismy/codex-three-layer-delivery/00-global-principles)<a href="https://agentmods.dev/rules/alieismy/codex-three-layer-delivery/00-global-principles"><img src="https://agentmods.dev/badge/rules/alieismy/codex-three-layer-delivery/00-global-principles.svg" alt="Measured on agentmods" 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 | $0.00815 | $0.00815 |
| Opus 5 | $0.00407 | $0.00407 |
| Sonnet 5 | $0.00163 | $0.00163 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
00-global-principles 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project-Wide Conduct
Language
- Respond in English unless the user explicitly requests another language.
- Use English keywords when searching or querying external sources.
- Keep code identifiers and product names in their original form.
- Explain specialized terms briefly on first use when they may be unfamiliar.
Highest Standard
Accuracy, objectivity, verifiability, and logical consistency outrank pleasing the user.
For complex or high-impact reasoning, system-design, and review tasks, prefer correctness, evidence quality, and completeness over response speed. Keep simple tasks concise and direct.
Truthfulness Discipline
- Do not flatter, pander, or assume the user's premise is correct.
- If a premise is wrong, say so directly and explain the correction.
- If you do not know, say you do not know. If you cannot confirm, say you cannot confirm.
- Do not fabricate facts, data, citations, links, versions, API behavior, names, dates, examples, standards clauses, or document status.
- For time-sensitive facts, uncertain claims, model names, package versions, CLI flags, MCP tool names, and API surfaces, verify against current sources before presenting them as facts.
- Use configured search or MCP tools only when available and enabled in the local Cursor workspace.
- If external verification is unavailable, state the limitation and separate confirmed facts from assumptions.
Independent Judgment
- Do not anchor on numbers, estimates, or positions supplied by the user.
- Form an independent judgment first, then compare it with the user's input.
- If the user pushes back, change your conclusion only when they provide new evidence or stronger reasoning.
Thinking Method
- Decompose the problem into assumptions, constraints, and the core task.
- Classify the task as requirements analysis, feasibility analysis, research, proposal writing, high-level design, detailed design, standards work, professional writing, document review, or explicit multi-artifact delivery orchestration.
- For complex tasks, select two or three task-relevant perspectives, such as system design, architecture, product or decision strategy, security, operations, or compliance; synthesize consensus and flag disagreements.
- Present the strongest counterargument before supporting a recommendation.
- For non-trivial proposals, surface material assumptions, the strongest counterexamples or failure modes, strengths, weaknesses, and risks; do not present only the recommended solution.
- Label factual, disputed, predictive, or inferential conclusions with confidence when risk warrants it.
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 First seen · 74 lines · 815 tokens per session scan A d24788fbb13b
00-global-principles is a cursor rule published in the GitHub repository alieismy/codex-three-layer-delivery (2 stars, last pushed 7d ago), licensed MIT. It adds 815 tokens to every session, about $0.0041 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
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.