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/01-engineering-discipline)<a href="https://agentmods.dev/rules/alieismy/codex-three-layer-delivery/01-engineering-discipline"><img src="https://agentmods.dev/badge/rules/alieismy/codex-three-layer-delivery/01-engineering-discipline.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 | $0.00841 | $0.00841 |
| Opus 5 | $0.00420 | $0.00420 |
| Sonnet 5 | $0.00168 | $0.00168 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
01-engineering-discipline 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document Delivery Discipline
Think Before You Write
- State assumptions explicitly when they affect requirements, feasibility, design, standards, or review conclusions.
- Read target documents first, then upstream requirements, feasibility reports, proposals, standards, glossaries, review comments, and constraints.
- Preserve source text before restructuring it. Do not silently rewrite user intent, clause wording, or stakeholder decisions.
- If a change affects document structure, terminology, authority, or traceability, provide a brief plan first.
- If multiple valid approaches have different trade-offs, recommend one and explain why.
Minimal Change Principle
- Prefer the smallest necessary document change.
- Reuse existing templates, terminology, numbering, review tables, directory structure, and document conventions.
- Do not add sections or process overhead because a future need is merely possible.
- Do not reformat unrelated content.
- Clean up inconsistencies caused by your change; leave pre-existing unrelated issues alone.
- Respect
.gitignore,.ignore,.rgignore, and tool-specific ignore rules by default. Inspect dependency directories, generated code, build outputs, caches, coverage output, or packaged artifacts only when the task or evidence requires it, and keep that access bounded. - Preserve the target file's encoding, line endings, and local formatting. Do not run repository-wide formatters, auto-fixes, or mechanical reordering unless explicitly requested or required by a project validation entry point. Update dependencies and lockfiles only when an approved dependency change requires it.
Goal-Driven Execution
Convert vague document tasks into verifiable goals:
| Request | Verifiable goal |
|---|---|
| Analyze requirements | PRD/SRS items with priority, assumptions, exclusions, and acceptance criteria |
| Assess feasibility | Feasible / conditionally feasible / not feasible conclusion with evidence, conditions, and risks |
| Write proposal | Candidate solution comparison and justified recommendation |
| Write detailed design | Interfaces, data, flows, errors, security, and unresolved decisions |
| Review document | Severity-graded findings with evidence, impact, and recommendations |
| Review standard | Exact clause references and normative replacement wording where possible |
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 Changed · +4 lines · +137 tokens per session 73471dfa8f3e
- 6d ago First seen · 59 lines · 704 tokens per session scan A 4846922a9c0e
01-engineering-discipline is a cursor rule published in the GitHub repository alieismy/codex-three-layer-delivery (2 stars, last pushed 6d ago), licensed MIT. It adds 841 tokens to every session, about $0.0042 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-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
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.