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/VoTruongDanh/Skills-AgentWrote 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/votruongdanh/skills-agent/enhance)<a href="https://agentmods.dev/rules/votruongdanh/skills-agent/enhance"><img src="https://agentmods.dev/badge/rules/votruongdanh/skills-agent/enhance.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 | $0.00058 | $0.00786 |
| Opus 5 | $0.00029 | $0.00393 |
| Sonnet 5 | $0.00012 | $0.00157 |
| Haiku 4.5 | $0.00006 | $0.00079 |
Grade A, and why
enhance 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Protocol
START: Read .ai-memory.md from project root. Check past enhancements, known pain points, tech debt notes, performance baselines, and architecture decisions.
END: Update .ai-memory.md using Memory Compaction Rules with: what changed, impact, tradeoffs, and remaining tech debt.
Goal
Improve an existing implementation without breaking working behavior.
Agent Routing
- If enhancing performance → read
.kiro/skills/agents/agents/performance-optimizer.mdand apply its knowledge - If tightening security → read
.kiro/skills/agents/agents/security-auditor.mdand apply its knowledge - If improving UI/UX → read
.kiro/skills/agents/agents/frontend-specialist.mdand apply its knowledge - If refactoring backend/API → read
.kiro/skills/agents/agents/backend-specialist.mdand apply its knowledge - If improving database queries → read
.kiro/skills/agents/agents/database-architect.mdand apply its knowledge
Socratic Gate
Before enhancing, verify:
- What specific aspect needs improvement? (performance, security, UX, maintainability?)
- What is the current pain point or metric?
- Are there existing tests that must continue to pass? If any answer is unclear, ASK before proceeding.
Workflow
- Read Memory — Load
.ai-memory.mdfor project context and past enhancement history. - Understand the current state and pain points.
- Identify high-impact improvements in quality, maintainability, performance, reliability, or UX.
- Prioritize improvements by value versus effort.
- Implement or recommend the top changes.
- Explain tradeoffs and validation steps.
- Quality Gate — Read
.kiro/skills/_scripts/checklist.mdand verify enhancements don't break existing behavior. - Update Memory — Save enhancement details and outcomes to
.ai-memory.md.
Checklist
- Current state documented
- Pain points identified
- Improvements prioritized by value/effort
- Existing behavior preserved
- Tradeoffs explained
- Tests still passing
- Memory file updated
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 · +3 lines 16855beca26f
- 7d ago First seen · 63 lines · 58 tokens per session scan A 489f450ffd0c
enhance is a cursor rule published in the GitHub repository VoTruongDanh/Skills-Agent (2 stars, last pushed 3d ago), licensed MIT. It adds 58 tokens to every session and 786 once invoked, about $0.0003 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-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.