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/GoranErhartic/backend-onboardingWrote 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/goranerhartic/backend-onboarding/engineering-rule)<a href="https://agentmods.dev/rules/goranerhartic/backend-onboarding/engineering-rule"><img src="https://agentmods.dev/badge/rules/goranerhartic/backend-onboarding/engineering-rule/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/goranerhartic/backend-onboarding/engineering-rule"><img src="https://agentmods.dev/badge/rules/goranerhartic/backend-onboarding/engineering-rule.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 | $0.00810 | $0.00810 |
| Opus 5.5 | $0.00324 | $0.00324 |
| Sonnet 5.5 | $0.00162 | $0.00162 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
engineering-rule 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 1mo 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering Defaults
Apply senior-level engineering judgment: deliberate, calibrated, explicit about trade-offs. Never silently guess.
1. Docs-first workflow — scaled to task size
If .cursor/onboarding-docs/CURSOR-ONBOARDING.md exists, consult the navigation docs before exploring source — scaled to the task:
| Task size | Examples | Read first |
|---|---|---|
| Trivial | typo, rename, one-line fix | nothing — go straight to the file |
| Non-trivial | feature, multi-file fix, new endpoint | CURSOR-ONBOARDING.md (manifest) + QUICK_REFERENCE.md |
| Architectural | new module, cross-cutting change, contract or migration change | manifest + quick reference + the tier-2 docs the manifest's Documentation Index points to for this area |
- The manifest is the single source of truth for which docs exist and what each covers. If the manifest and this rule disagree, trust the manifest.
REFERENCE_METADATA.jsonis a machine index — use it for structured lookups (endpoints, entities, services) only when helpful.- Docs orient you; they are a map, not the territory. Verify against actual source before relying on them.
- Existing project
AGENTS.mdfiles remain authoritative. Before exploring a source subtree, read the applicable files from root to that subtree; use the manifest'sProject Agent Instructionsindex to locate them when present. Do not duplicate their instructions in onboarding docs. - Manifest missing: proceed with normal exploration. For non-trivial work, mention once that navigation docs are absent and offer to run the
onboarding-codebaseskill — do not run it unprompted.
2. Engineering defaults
- Match existing patterns first. Before introducing a new pattern, library, or abstraction, check how the codebase already solves the same problem — and follow it. The repo's own tooling (linter config, test framework, commit style) is the authority on conventions.
- Boring by default. YAGNI. No new abstraction without evidence (3+ call sites or a demonstrated pain point). Prefer the simplest thing that works.
- Articulate trade-offs. For non-trivial changes, present 2–3 approaches with their costs before choosing. Never silently pick.
- Check blast radius. Backward compatibility: API contracts, data models, migrations, existing callers, deploy order. State what could break and how to roll back.
- Define the verification plan. Which tests run, what to check manually, what to watch in logs/metrics. No "done" without it.
- Handle errors by intent. Recoverable → handle and continue. Fatal → fail fast. Never blanket-catch to silence.
- Flag risks explicitly. Call out security, performance, and data-loss exposure in the summary.
- Ask when intent is ambiguous. One sharp question beats a confident wrong implementation.
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.
- 1mo ago Changed · -12 lines · +773 tokens per session 38cf7d5d84dc
- 2mo ago First seen · 61 lines · 37 tokens per session scan A 88ec440fb0d1
engineering-rule is a cursor rule published in the GitHub repository GoranErhartic/backend-onboarding (11 stars, last pushed 1mo ago), licensed MIT. It adds 810 tokens to every session, about $0.0032 per session on Opus 5.5. 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.
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.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).