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.
npx agentmods add rules/alieismy/codex-three-layer-delivery/02-spec-injectiongit 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/02-spec-injection)<a href="https://agentmods.dev/rules/alieismy/codex-three-layer-delivery/02-spec-injection"><img src="https://agentmods.dev/badge/rules/alieismy/codex-three-layer-delivery/02-spec-injection.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 | $0.00477 | $0.00477 |
| Opus 5 | $0.00238 | $0.00238 |
| Sonnet 5 | $0.00095 | $0.00095 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
02-spec-injection 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 5d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Injection
Project specs are stored in the repository so Cursor Agent can load consistent conventions across sessions.
Spec Hierarchy
| Level | Carrier | Loading method |
|---|---|---|
| User global | Cursor User Rules | Applied from Cursor settings |
| Project specs | .cursor/rules/*.mdc |
Project-scoped rules |
| Module specs | Nested .cursor/rules/ or globs in .mdc frontmatter |
Scoped to matching paths |
| Task capabilities | .cursor/skills/rd-*/SKILL.md |
Invoked by Cursor Agent when relevant |
| Interoperable fallback | AGENTS.md |
Plain markdown alternative where appropriate |
Rule Authoring
- Keep rules focused, actionable, and under 500 lines.
- Project Rules must use
.mdc; declaredescription,globs, andalwaysApplyin frontmatter as appropriate. - Split large concepts into composable rules instead of one broad rule.
- Prefer concrete constraints, scripts, paths, and examples over vague preferences.
- Do not store secrets, private URLs, or personal credentials in rules.
Spec Check Requirements
Before requirements, feasibility, design, standards, or review work:
- Check
.cursor/rules/for project conventions. - Check relevant skills in
.cursor/skills/. - Check existing templates, glossaries, review forms, standards references, and prior decisions before creating new rules.
- Persist durable project decisions as rules only when they are reusable.
Spec Maintenance
.cursor/rules/is for agent behavior and project constraints.README.mdis for humans: what the project is, why it exists, and how to start.- Avoid duplicating the same content between rules and README.
- Before adding a rule, search for an equivalent existing rule and tighten it instead of duplicating it.
- Add a durable rule only when it traces to an explicit project requirement, a recurring observed failure, or a material project risk, and state how compliance can be reviewed or verified.
- Skill frontmatter
descriptionis the trigger summary. It should start with trigger conditions and stay short.
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.
- 5d ago First seen · 45 lines · 477 tokens per session scan A 0d575cd11263
02-spec-injection is a cursor rule published in the GitHub repository alieismy/codex-three-layer-delivery (2 stars, last pushed 5d ago), licensed MIT. It adds 477 tokens to every session, about $0.0024 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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.