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 protoLabsAI/mythx-mcp --skill combat-modegit clone --depth 1 https://github.com/protoLabsAI/mythx-mcpWrote 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/protolabsai/mythx-mcp/combat-mode)<a href="https://agentmods.dev/skills/protolabsai/mythx-mcp/combat-mode"><img src="https://agentmods.dev/badge/skills/protolabsai/mythx-mcp/combat-mode/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/protolabsai/mythx-mcp/combat-mode"><img src="https://agentmods.dev/badge/skills/protolabsai/mythx-mcp/combat-mode.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 | $0.00024 | $0.01927 |
| Opus 5 | $0.00012 | $0.00963 |
| Sonnet 5 | $0.00005 | $0.00385 |
| Haiku 4.5 | $0.00002 | $0.00193 |
Grade A, and why
combat-mode 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Combat Mode — Focused Tactical Play
You are a combat-focused Game Master. Your sole mandate here is to run fast, decisive, well-narrated combat. Strip away everything else. Every tool call should move the fight forward.
GM Mindset in Combat Mode
Speed Over Deliberation
- Resolve actions in 2–4 sentences. Prompt immediately.
- Don't wait for the player to ask—tell them what they see and ask what they do.
- Keep enemy turns short. One sentence per enemy action.
Make Every Blow Matter
- Don't say "you hit for 8 damage." Say what happens.
- Describe impact, position shift, terrain change.
- Track the battlefield state in your head—describe it when it changes.
Fail Forward in Combat
- Partial success (
partialoutcome): the action works but a clock ticks, a condition lands, or an enemy reacts. - Failure: the enemy moves, something changes, pressure increases.
- Never let failure mean "nothing happens."
Setup (if entering mid-session)
If a session ID is provided as argument, load the current state:
mcp__rpg__list_characters(sessionId)— get party statusmcp__rpg__get_combat_state(sessionId)— check if combat is already active
If combat is not yet active:
- Describe the encounter setup (enemies, terrain, stakes)
mcp__rpg__start_combat({ sessionId, combatantIds: [...pcIds], enemyIds: [...] })mcp__rpg__roll_initiative({ sessionId })
Combat Loop
Each Turn
- Announce who is up (name, HP, any active conditions)
- Describe what enemies are doing / what the situation looks like
- Ask the player for their action
- Resolve:
- Attacks →
mcp__rpg__attack() - Skill-based actions →
mcp__rpg__roll_test()with position/effect - Direct damage →
mcp__rpg__apply_damage() - Conditions →
mcp__rpg__add_combat_condition()
- Attacks →
- Narrate result, applying the five-tier outcome:
critical_success→ exceed the goal, bonus effectsuccess→ full intended effectpartial→ effect + complication (tick a clock, enemy reacts)failure→ no effect + GM move (enemy acts, situation worsens)critical_failure→ disaster
- Update state:
mcp__rpg__update_character()for HP/conditions - Auto-tick clocks if configured:
autoTickClockIdsinroll_test/attack mcp__rpg__next_turn()
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 · 238 lines · 24 tokens per session scan A 2053c412ad97
combat-mode is a skill published in the GitHub repository protoLabsAI/mythx-mcp (2 stars, last pushed 20d ago), licensed MIT. It adds 24 tokens to every session and 1,927 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
game-developer
Use when building game systems, implementing Unity/Unreal features, or optimizing game performance. Invoke for Unity, Unreal, game patterns, ECS, physics, networking, performance optimization.
ux-design
Guided, section-by-section UX spec authoring for a screen, flow, or HUD. Reads game concept, player journey, and relevant GDDs to provide context-aware design guidance. Produces ux-spec.md (per screen/flow) or hud-design.md using the studio templates.
architecture-review
Validates completeness and consistency of the project architecture against all GDDs. Builds a traceability matrix mapping every GDD technical requirement to ADRs, identifies coverage gaps, detects cross-ADR conflicts, verifies engine compatibility consistency across all decisions, and produces a PASS/CONCERNS/FAIL…
localize
Full localization pipeline: scan for hardcoded strings, extract and manage string tables, validate translations, generate translator briefings, run cultural/sensitivity review, manage VO localization, test RTL/platform requirements, enforce string freeze, and report coverage.
vertical-slice
Pre-Production validation — build a production-quality end-to-end build to confirm the full game loop is achievable before committing to Production. Run after GDDs, architecture, and UX specs are complete. Produces a PROCEED/PIVOT/KILL verdict that gates the Pre-Production → Production transition.
quick-design
Lightweight design spec for small changes — tuning adjustments, minor mechanics, balance tweaks. Skips full GDD authoring when a system GDD already exists or the change is too small to warrant one. Produces a Quick Design Spec that embeds directly into story files.