Agent skill

Gm Combat

by Sstobo in Sstobo/Claude-Code-Game-Master

D&D-kit combat mechanics — initiative, attack/damage resolution, XP-by-CR awards, combat modifiers, and death saves.

Custom licenceAuto-check passed

Install Gm Combat

skills CLI
$ npx skills add Sstobo/Claude-Code-Game-Master --skill gm-combat -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Sstobo/Claude-Code-Game-Master gm-combat --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Sstobo/Claude-Code-Game-Master.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/gm-combat .claude/skills/gm-combat && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
gm-combat
GitHub stars
155
Token cost
~686 tokens
SKILL.md length
350 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
Custom licence

At a glance

D&D-kit combat mechanics — initiative, attack/damage resolution, XP-by-CR awards, combat modifiers, and death saves.

  • Works in 4 steps: Get enemy stats… → Initiative: uv run python lib/dice.py… → Each turn: attack 1d20+bonus vs AC; on… → …
  • SKILL.md covers Flow, XP by Challenge Rating, Modifiers and Death & Dying
  • Calls bash and uv

What it does

Gm Combat is an agent skill from Sstobo/Claude-Code-Game-Master. D&D-kit combat mechanics — initiative, attack/damage resolution, XP-by-CR awards, combat modifiers, and death saves. Load when a hostile action is declared or combat starts in a campaign whose World Kit is dnd5e. For non-D&D kits, use the generic core (gamecore.py) and the active ruleset instead.

Its SKILL.md is about 690 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Total conversion for Claude Code. Use RAG and the RPG ruleset apis to play a persistent adventure in any book or world of your choosing.

Example prompts

  • “/gm-combat”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Get enemy stats (features/dnd-api/monsters/dnd_monster.py "[creature]" --combat or quick: AC 13, HP 15, +3, 1d6+1).
  2. Initiative: uv run python lib/dice.py "1d20+[dex]" per combatant; order high→low.
  3. Each turn: attack 1d20+bonus vs AC; on hit roll damage; update HP via gm-combat.sh hp.
  4. Resolution: award XP, handle loot (persist BEFORE narrating), advance time.

What it can do on your machine

Read from SKILL.md and the folder at commit dea9931. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • bash
    • uv

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gm Combat loads about 686 tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 350 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~77
When it runs · the whole SKILL.md, loaded when a task matches
~686

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 350 words (~686 tokens).

“STEP 0 — KIT GUARD. If the scene-context KIT block is not dnd5e, close this skill and resolve the fight through the generic core (game_core) and the active ruleset.”

— opening of SKILL.md by Sstobo, Custom licence
name
gm-combat

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/gm-combat of Sstobo/Claude-Code-Game-Master.

Open the folder on GitHubat commit dea9931

Compare with similar skills

Gm Combat next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Gm Combat compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gm Combat this skillSstobo/Claude-Code-Game-Master155—~686Automated safety check: PassCustom licence
Block Kitopenclaw/openclaw392k—~624Automated safety check: PassMIT
Kit AutomationComposioHQ/awesome-claude-skills77k3 repos~715Automated safety check: PassNone
Context Kitsickn33/agentic-awesome-skills47k1 repos~1.5kAutomated safety check: PassMIT
Initiate SetupNousResearch/hermes-agent252k—~2.3kAutomated safety check: PassMIT
Attack Tree Constructionwshobson/agents40k8 repos~623Automated safety check: PassMIT

Similar skills

  • Block Kit

    openclaw/openclaw

    Use proactively for structured or interactive Slack replies, and when asked to author or validate native Slack Block Kit JSON.

    392k GitHub stars~624 tokensUpdated today
    Auto-check passed
  • Kit Automation

    ComposioHQ/awesome-claude-skills

    Automate Kit tasks via Rube MCP (Composio). An agent skill from ComposioHQ/awesome-claude-skills.

    77k GitHub starsUsed in 3 repos~715 tokens
    Productivity & AutomationAuto-check passed
  • Context Kit

    sickn33/agentic-awesome-skills

    Evaluate, adapt, and safely install Context Kit personal context artifacts for Claude Code or adjacent agent workflows.

    47k GitHub starsUsed in 1 repo~1.5k tokens
    Auto-check passed
  • Initiate Setup

    NousResearch/hermes-agent

    Run the first-run setup chat in the Hermes desktop app. An agent skill from NousResearch/hermes-agent.

    252k GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • Builds attack trees that map how an attacker could reach a goal, with AND and OR nodes and cost, time, skill and detection ratings, to find defense gaps.

    40k GitHub starsUsed in 8 repos~623 tokens
    SecurityAuto-check passed
  • Detecting Kerberoasting Attacks

    mukul975/Anthropic-Cybersecurity-Skills

    Detect Kerberoasting attacks by monitoring for anomalous Kerberos TGS requests (Event ID 4769) targeting service accounts with SPNs, which attackers request offline to crack service account passwords.

    34k GitHub stars~914 tokensUpdated 1 mo ago
    SecurityAuto-check passed

More from Sstobo/Claude-Code-Game-Master

All 8 skills in this repo
  • Gm Social

    Sstobo/Claude-Code-Game-Master

    Social / NPC interaction workflow — load NPC context, attitude check, social mechanics (Persuasion/Deception/Intimidation/Insight DCs), and persisting NPC memory + consequences.

    155 GitHub stars~1k tokensUpdated 1 mo ago
    Auto-check passed
  • Gm Skills

    Sstobo/Claude-Code-Game-Master

    Skill-check resolution — when to roll, the DC ladder, fail-forward philosophy, and margin-based consequences.

    155 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed
  • Gm Dungeon

    Sstobo/Claude-Code-Game-Master

    Dungeon exploration — lightweight (narrative, default) vs structured (per-room JSON) modes, exit/obstacle handling, and ASCII map symbols.

    155 GitHub stars~388 tokensUpdated 1 mo ago
    Auto-check passed
  • Gm Craft

    Sstobo/Claude-Code-Game-Master

    The Art of Game Mastering — narration, NPC, pacing, and improvisation wisdom that makes a session feel magical.

    155 GitHub stars~2k tokensUpdated 1 mo ago
    Auto-check: warnings
  • Gm Levelup

    Sstobo/Claude-Code-Game-Master

    D&D-kit leveling — XP thresholds, the level-up ceremony, hit dice by class, and ASI/feat/subclass handling.

    155 GitHub stars~345 tokensUpdated 1 mo ago
    Auto-check passed
  • Gm Spellcasting

    Sstobo/Claude-Code-Game-Master

    D&D-kit spellcasting mechanics — spell slots by level, casting resolution, and concentration.

    155 GitHub stars~293 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Gm Combat

What does Gm Combat do?

D&D-kit combat mechanics — initiative, attack/damage resolution, XP-by-CR awards, combat modifiers, and death saves. Gm Combat is an agent skill from Sstobo/Claude-Code-Game-Master. D&D-kit combat mechanics — initiative, attack/damage resolution, XP-by-CR awards, combat modifiers, and death saves.

How do I install Gm Combat in Claude Code?

Run `npx skills add Sstobo/Claude-Code-Game-Master --skill gm-combat -a claude-code`. Or copy the skill folder (.claude/skills/gm-combat in Sstobo/Claude-Code-Game-Master) into .claude/skills/gm-combat in your project. Claude Code loads it when a task matches its description.

How do I install Gm Combat in Codex?

Run `npx skills add Sstobo/Claude-Code-Game-Master --skill gm-combat -a codex`. Or copy the skill folder (.claude/skills/gm-combat in Sstobo/Claude-Code-Game-Master) into .agents/skills/gm-combat in your project. Codex loads it when a task matches its description.

Can I use Gm Combat in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Sstobo/Claude-Code-Game-Master --skill gm-combat -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gm-combat, .gemini/skills/gm-combat, .github/skills/gm-combat and .opencode/skills/gm-combat in your project.

What does Gm Combat need to run?

Going by SKILL.md and its folder, Gm Combat needs the command-line tools its instructions call (bash and uv). Our summary lists: Python 3.

Does Gm Combat access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Gm Combat safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Gm Combat use?

Gm Combat has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Gm Combat use?

About 686 tokens (SKILL.md is roughly 2.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Gm Combat?

Skills that share tags, products or a category with Gm Combat: Block Kit (openclaw/openclaw, 392k stars), Kit Automation (ComposioHQ/awesome-claude-skills, 77k stars), Context Kit (sickn33/agentic-awesome-skills, 47k stars) and Initiate Setup (NousResearch/hermes-agent, 252k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gm Combat?

Sstobo (a GitHub user) maintains it in Sstobo/Claude-Code-Game-Master, which has 155 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on August 16, 2026.

Source: Sstobo/Claude-Code-Game-Master on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.