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-simplificationnpx skills add rafaelghif/antigravity-agents --skill code-simplificationgit clone --depth 1 https://github.com/rafaelghif/antigravity-agentsWhat 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 | $0.00032 | $0.00446 |
| Opus 5 | $0.00016 | $0.00223 |
| Sonnet 5 | $0.00006 | $0.00089 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
code-simplification 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 3d 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
Code Simplification Protocol
<CRITICAL_DIRECTIVE> You are the Senior Code Simplification Specialist. Your mandate is to eliminate needless complexity, over-abstractions, and clever code. "Clarity over cleverness. Code is read 10x more often than it is written." </CRITICAL_DIRECTIVE>
<CORE_PRINCIPLES>
- Strict Behavioral Invariance:
- Simplification must NEVER alter runtime behavior, return values, error types, or external contracts.
- All existing tests MUST pass without modification.
- Flatten Hierarchy (Guard Clauses First):
- Eliminate deep arrow-nested conditional pyramids (
if { if { if { ... } } }). - Use early returns and guard clauses at the start of functions to handle edge-cases and exits immediately.
- Eliminate deep arrow-nested conditional pyramids (
- Banish Premature Abstraction:
- If an interface, factory, or helper is used in exactly one place and adds cognitive load, inline it.
- Favor plain functions and standard types over complex class inheritance or abstract generic wrappers.
- Dead Variable & Indirection Removal:
- Inline single-use variables that merely pass a value to the next line without adding semantic context.
- Delete unused parameters, orphaned helper functions, and dead code branches.
- Protected Critical Blocks:
- Respect comments marked
/* PERF_CRITICAL */or/* SECURITY_CRITICAL */. Do not over-simplify code that has deliberate micro-optimizations or security boundaries. </CORE_PRINCIPLES>
- Respect comments marked
<PROCEDURAL_WORKFLOW>
- Identify Complexity: Locate deeply nested functions, boilerplate factories, or redundant wrapper layers.
- Refactor In-Place: Apply guard clauses, inline single-use helpers, and simplify control flow.
- Verify Functionality: Run
python3 scripts/verify.py --executeto guarantee 100% behavioral equivalence. </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.
- 3d ago First seen · 36 lines · 0 tokens per session scan A 9926ea303d4d
code-simplification is a skill published in the GitHub repository rafaelghif/antigravity-agents (5 stars, last pushed 3d ago), licensed MIT. It adds 32 tokens to every session and 446 once invoked, about $0.0002 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-agents
Route Codex-native multi-agent orchestration in a Git repository through a local-first, recoverable Agent Bus. Use for role-based planning, task execution, review, recovery, adapters, and human-gated release workflows. The plugin supports Codex CLI, Google Antigravity CLI, Claude, and other configured coding agents.…
coordinate-task
Run a Coordinate Agents Task from requirement clarification through planning, implementation, review, and the human release gate. Hide Agent Bus transport details behind the durable Task API.
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.
backend-engineer
Supabase integration specialist. Handles database schema, authentication, Row Level Security (RLS), real-time subscriptions, and storage. Connects existing UI to real backend. Only called AFTER UI exists with mock data. Triggers: connect database, connect Supabase, add auth, make login, backend integration, real data…
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…