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/mordilion/ai-instructions-and-promptsWrote 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/mordilion/ai-instructions-and-prompts/architecture)<a href="https://agentmods.dev/rules/mordilion/ai-instructions-and-prompts/architecture"><img src="https://agentmods.dev/badge/rules/mordilion/ai-instructions-and-prompts/architecture/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/mordilion/ai-instructions-and-prompts/architecture"><img src="https://agentmods.dev/badge/rules/mordilion/ai-instructions-and-prompts/architecture.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 | $0.00000 | $0.00456 |
| Opus 5 | $0.00000 | $0.00228 |
| Sonnet 5 | $0.00000 | $0.00091 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
architecture scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Bash Architecture
Scope: Apply these rules ONLY when working with shell scripts (
*.sh,*.bash,*.zsh,*.ksh,*.bats). These extend the general architecture guidelines.
1. Core Principles
- Single responsibility: One script = one job. Split reusable logic into libraries.
- Predictability: Prefer explicit inputs/outputs, clear exit codes, and deterministic behavior.
- Portability: Default to Bash; avoid relying on non-standard tools unless explicitly required.
2. Script Layout
- Entry point: Prefer a
main()function and call it at the bottom. - Sections order:
- Shebang + metadata/comments
- Strict mode + globals (constants)
- Helper functions
main()(or command dispatcher)main "$@"
- Libraries: Put reusable functions in
scripts/lib/*.sh(orlib/) and source them explicitly.
3. Configuration & Inputs
- Config: Prefer env vars and flags; allow config files only when necessary.
- CLI: Use
getoptsfor flags; document usage inusage()and return exit code2for CLI misuse. - I/O: Prefer explicit files/paths; avoid implicit cwd assumptions.
4. Exit Codes & Error Boundaries
- Exit codes: Use
0success,1generic failure,2usage/validation errors. - Error boundaries: Fail fast; validate prerequisites early (required commands, files, permissions).
- Logging: Standardize
log_info,log_warn,log_errorand write errors to stderr.
5. Composition
- Pipelines: Avoid deep pipelines; break into named functions for readability.
- Idempotency: For provisioning/deploy scripts, prefer idempotent steps (safe to re-run).
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 · 40 lines · 0 tokens per session scan A 2392731177b7
architecture is a cursor rule published in the GitHub repository mordilion/ai-instructions-and-prompts (1 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 456 tokens. 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.