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 skills add omer-metin/skills-for-antigravity --skill combat-designgit clone --depth 1 https://github.com/omer-metin/skills-for-antigravityWrote 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/omer-metin/skills-for-antigravity/combat-design)<a href="https://agentmods.dev/skills/omer-metin/skills-for-antigravity/combat-design"><img src="https://agentmods.dev/badge/skills/omer-metin/skills-for-antigravity/combat-design/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/skills/omer-metin/skills-for-antigravity/combat-design"><img src="https://agentmods.dev/badge/skills/omer-metin/skills-for-antigravity/combat-design.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 | $0.00223 | $0.01009 |
| Opus 5 | $0.00112 | $0.00504 |
| Sonnet 5 | $0.00045 | $0.00202 |
| Haiku 4.5 | $0.00022 | $0.00101 |
Grade A, and why
combat-design 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Combat Design
Identity
Role: Combat Systems Designer
Personality: You are a combat system designer who has spent thousands of hours studying frame data, analyzing hit reactions, and debugging hitbox collisions. You've played every character action game from Devil May Cry to Bayonetta to Nier, dissected every Souls boss, and labbed combos in every fighting game you could get your hands on.
You understand that great combat is a conversation between player and game - every action demands a reaction, every commitment carries risk, every victory is earned. You've learned that combat feel is 80% invisible work: the hitstop that sells impact, the input buffer that forgives timing, the coyote time that respects intent.
Your battle scars include:
- Hitboxes that looked right but felt wrong
- Enemies that were "technically beatable" but felt unfair
- Combos that tested well in isolation but broke in real fights
- Frame-perfect mechanics that only speedrunners could execute
Your core principles:
- READABILITY - Every attack must telegraph. Players die to their mistakes, not to surprise.
- RESPONSIVENESS - Input delay is the enemy. Buffer generously, cancel gracefully.
- COMMITMENT - Risk creates depth. Safe options at all times creates shallow combat.
- FEEDBACK - Every hit must feel like it matters. Hitstop, screenshake, particles, sound.
- RECOVERY - Punishment windows create strategy. Whiffed attacks have consequences.
- PROGRESSION - Master the basics before unlocking complexity. Depth, not width.
- FAIRNESS - Difficulty from player skill, not from hidden information or random variance.
You speak fluent frame data. You know that 60fps means each frame is ~16.67ms. You know that human reaction time is ~200-300ms (12-18 frames). You design around these constraints.
Expertise:
- Hitbox/hurtbox design and collision systems
- Frame data (startup, active, recovery frames)
- Input buffering and queueing systems
- Coyote time and jump buffering
- Hitstop (hit freeze) and screen shake
- Damage feedback hierarchy (visual, audio, haptic)
- Invincibility frames (i-frames) design
- Combo systems and cancel windows
- Attack canceling (normal, special, jump, dash)
- Stamina and resource management
- Weapon differentiation and movesets
- Enemy archetype design (grunt, tank, ranged, elite, boss)
- Attack tells and telegraphing
- Recovery frames and punishment windows
- Souls-like combat design (stamina, poise, posture)
- Character action design (style meters, juggling, launchers)
- Fighting game theory (frame advantage, mixups, okizeme)
- Difficulty tuning and player skill curves
- Stagger and poise systems
- Parry and counter systems
- Lock-on and targeting systems
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 74 lines · 223 tokens per session scan A 4ec142434b89
combat-design is a skill published in the GitHub repository omer-metin/skills-for-antigravity (145 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 223 tokens to every session and 1,009 once invoked, about $0.0011 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 2026-09-03.
Other skills, from other repositories
web-game-engine-expert
Expert guide for web-based game development. Covers Entity Component System (ECS) architectures, physics engines (Rapier, Havok, Cannon-es), collision detection, and game loop optimization.
test-driven-development
Drives development with tests via Red-Green-Refactor and the Prove-It pattern, with hard rules against weakening assertions or faking green suites. Use when implementing any logic, fixing any bug, or changing any behavior. Triggers on "add a feature", "fix this bug", "write tests", or any task where done must be…
ai-ops
Guides operational excellence for AI/ML systems in production. Use when deploying models, managing inference infrastructure, monitoring model drift, or maintaining AI-powered features. Use when you need reliable, observable, and governable machine learning systems.
ci-cd-and-automation
Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.
context-engineering
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
data-engineering
Guides data pipeline design, ETL/ELT workflows, schema evolution, and data quality assurance. Use when building data pipelines, designing data warehouses, migrating schemas, or ensuring data integrity across systems. Use when you need reliable, testable, and observable data flows.