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 skills/rafaelghif/antigravity-agents/code-qualitynpx skills add rafaelghif/antigravity-agents --skill code-qualitygit clone --depth 1 https://github.com/rafaelghif/antigravity-agentsWrote 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/skills/rafaelghif/antigravity-agents/code-quality)<a href="https://agentmods.dev/skills/rafaelghif/antigravity-agents/code-quality"><img src="https://agentmods.dev/badge/skills/rafaelghif/antigravity-agents/code-quality.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 | $0.00027 | $0.00836 |
| Opus 5 | $0.00014 | $0.00418 |
| Sonnet 5 | $0.00005 | $0.00167 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
code-quality 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 4d 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
<CRITICAL_DIRECTIVE> Enforce Staff-level procedural rigor, the Senior Ladder, and Enterprise-Grade software architecture. </CRITICAL_DIRECTIVE>
<THE_SENIOR_LADDER> The best code is the code never written. Before writing code, stop at the first rung that holds:
- Does this need to exist? -> Skip it (YAGNI).
- Already in codebase? -> Reuse existing helper/hook/type/component.
- Stdlib does it? -> Use standard library.
- Native platform feature? -> Native HTML5/CSS/DB constraint over heavy libraries (e.g.
<input type="date">over picker lib). - Existing dependency? -> Use installed libraries; never add new dependencies for trivial tasks.
- Can it be one line? -> One line.
- Only then: write the minimum code that works. Root-cause fix only: grep all callers and fix at the shared root, never patch leaf symptoms. </THE_SENIOR_LADDER>
<ENTERPRISE_STANDARDS>
- DRY & Single Source of Truth (SSOT): Absolutely NO duplicate logic. Re-use existing project hooks, utilities, and components. If logic repeats >= 2 times, extract it to a shared module immediately.
- Project Pattern Harmony: NEVER introduce pattern schizophrenia. Before coding, inspect existing sibling files. Strictly adhere to the project's established conventions for state management, data-fetching, error handling, directory structure, and styling.
- SOLID & Clean Architecture: Enforce Single Responsibility (SRP) and Dependency Inversion (DIP). Maintain strict isolation between UI presentation, domain business logic, and infrastructure/data access.
- Senior Defensive Engineering:
- Prevent race conditions and memory leaks (clean up event listeners, timers, abort stale requests with AbortController).
- Strict runtime data validation (Zod, Pydantic) on all external inputs, APIs, and route params.
- Comprehensive error boundaries with structured domain errors (no silent failures or ad-hoc console.log).
- Cyclomatic Complexity & Algorithmic Supremacy: Keep functions atomic with shallow indentation. Default to O(1) lookups instead of O(N^2) loops. Memoize expensive operations.
- Zero-Tolerance Anti-Patterns: NO
anytypes in TypeScript. NO broadexcept Exception:blocks in Python. NO inline CSS styles or ad-hoc duplicate UI primitives. - Feature Completeness (Anti-Dummy): 100% complete production implementations. NO placeholders, mock arrays, or
// TODOstubs. Handle loading, empty, and error states gracefully. - Security & Secrets: All credentials, tokens, and sensitive configs MUST come from environment variables. </ENTERPRISE_STANDARDS>
<PROCEDURAL_WORKFLOW>
- Pattern Reconnaissance: Search and read existing sibling files to identify established project patterns (state, API, styling, error handling).
- Ladder Check: Evaluate the 7-rung Senior Ladder before adding new code or dependencies.
- Reuse Audit: Check for existing shared components, hooks, or utilities before creating new ones to maintain DRY.
- Context Acquisition: Understand imports, contracts, and type definitions before modifying code.
- Minimal Delta Enforcement: Implement ONLY the requested feature with maximum architectural elegance.
- Test Gap Analysis & TDD: Ensure tests exist and cover all edge cases before modifying implementation.
- Local Verification: Run stack linter, typecheck, and test runner via
python3 scripts/verify.py --execute. - Diff Review: Verify zero duplicate code, zero pattern deviations, and complete feature coverage. </PROCEDURAL_WORKFLOW>
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.
- 4d ago First seen · 46 lines · 27 tokens per session scan A 3e784d451cfa
code-quality is a skill published in the GitHub repository rafaelghif/antigravity-agents (5 stars, last pushed 4d ago), licensed MIT. It adds 27 tokens to every session and 836 once invoked, about $0.0001 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 skills, from other repositories
coordinate-recover
Diagnose and safely resume Coordinate Agents Tasks after executable failure, non-zero exit, timeout, stale claim, processing message, or Implementer ERROR. Recovery is explicit and never an automatic retry loop.
coordinate-setup
Discover coding CLIs on the current computer and configure a Coordinate Agents implementation agent. Use for setup, executable checks, registered agents, user-level configuration, and project-over-user precedence.
dev-engineer
Adds logic, state management, TypeScript types, and CRUD operations to UI. Works AFTER ui-first-builder creates the interface. Implements Zustand stores, form handling with React Hook Form + Zod, and prepares for backend connection. Triggers: add logic, add functionality, make it work, state management, form…
platform-specialist
Doc-driven platform integration expert. Converts a web app to LINE MINI App (LIFF SDK), PWA (Next.js 16), and Capacitor (iOS/Android). Expo & Tauri are secondary/legacy. ปรัชญาหลัก: ดึง docs จริงล่าสุดก่อนเขียนโค้ดเสมอ — ไม่ freeze snippet ที่จะ rot. Triggers: "LINE MINI App", "LIFF", "LINE OA", "convert to app"…
premium-experience
Premium app generation that creates WOW-factor experiences. Multi-page apps with smooth animations, zero TypeScript errors, and production-ready quality. Lovable-style experience: one prompt, complete app, instant delight. MUST be used alongside vibe-orchestrator for new projects.
smart-routing
Intelligent request routing for /toh command. Analyzes user intent, assesses confidence, surveys the runtime (2-step, per orchestration-protocol), and routes to the appropriate agent(s). Memory-first approach ensures context awareness. Triggers: /toh command, natural language requests, ambiguous inputs.