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/giang6283623/minimal-vibe-coding-kitWrote 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/giang6283623/minimal-vibe-coding-kit/070-proportional-effort)<a href="https://agentmods.dev/rules/giang6283623/minimal-vibe-coding-kit/070-proportional-effort"><img src="https://agentmods.dev/badge/rules/giang6283623/minimal-vibe-coding-kit/070-proportional-effort/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/giang6283623/minimal-vibe-coding-kit/070-proportional-effort"><img src="https://agentmods.dev/badge/rules/giang6283623/minimal-vibe-coding-kit/070-proportional-effort.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 | $0.00362 | $0.00362 |
| Opus 5 | $0.00181 | $0.00181 |
| Sonnet 5 | $0.00072 | $0.00072 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
070-proportional-effort 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 9d 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
Proportional effort rules
- Match process weight to task size; review must never cost more than the change itself.
- Triage each request in one line before working:
- trivial: typo, comment, one-liner, no agent-surface impact. Edit, validate, report. No plan, no subagents, no review loops.
- small: one file or one skill document. Two-line plan, edit, validate.
- medium: several files or shared behavior. Short plan, edit, validate, one diff self-review.
- large or risky: installers, validators, security, agent surfaces, destructive paths. Full plan plus the skills and probes the security rules require.
- Never launch parallel-analysis, graph orchestration, multi-agent review, visual loops, or e2e suites for trivial or small tasks unless the user asks.
- Visual and e2e gate: never run
visual-design-loopor full e2e suites by default. Score 0-2 per question: (1) user-visible surface changed, (2) outcome depends on subjective visual judgment, (3) a visual regression could reach users unnoticed by existing tests. - Score 0-2: skip and rely on the
backbone.ymlvalidation command. Score 3-4: one screenshot check, at most one targeted fix, no loop. Score 5-6: propose the run with budget and estimated cost, then wait for explicit user approval. - Always report the gate in one line, for example: "visual gate 2/6: skipped".
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.
- 9d ago First seen · 18 lines · 362 tokens per session scan A 6e62ff664994
070-proportional-effort is a cursor rule published in the GitHub repository giang6283623/minimal-vibe-coding-kit (21 stars, last pushed 11d ago), licensed MIT. It adds 362 tokens to every session, about $0.0018 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 2026-08-30.
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.
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.