craft

craft is a skill for Claude Code from syaor4n/seedcraft. It costs 101 tokens per session (1,861 once invoked), scanned A, original, MIT.

A tool that turns Claude Code session statistics into a Minecraft world seed whose starting biome reflects those statistics. Minecraft is a game built around exploring and shaping procedurally generated worlds.

In plain words
What is it for?
Use it to analyze local Claude Code session files, create a climate profile, and find a matching seed through the SeedCraft service or its local fallback database.
Why use it?
It gives coding activity a playful visual interpretation based on measures such as messages, tool calls, session time, projects, and edits.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the seedcraft plugin — 1 skill shipped together

Good fit Use it to analyze local Claude Code session files, create a climate profile, and find a matching seed through the SeedCraft service or its local fallback database.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add syaor4n/seedcraft
Claude Code
/plugin install seedcraft

Made for: Claude Code.

Or install seedcraft, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

agentmods badge for craft

README.md
[![agentmods](https://agentmods.dev/badge/skills/syaor4n/seedcraft/seedcraft/github.svg)](https://agentmods.dev/skills/syaor4n/seedcraft/seedcraft)
Your own site
<a href="https://agentmods.dev/skills/syaor4n/seedcraft/seedcraft"><img src="https://agentmods.dev/badge/skills/syaor4n/seedcraft/seedcraft/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.

agentmods 80×15 button for craft

Your own site · 80×15
<a href="https://agentmods.dev/skills/syaor4n/seedcraft/seedcraft"><img src="https://agentmods.dev/badge/skills/syaor4n/seedcraft/seedcraft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,861 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00101 $0.01861
Opus 5 $0.00051 $0.00931
Sonnet 5 $0.00020 $0.00372
Haiku 4.5 $0.00010 $0.00186

Measured 10d ago against content hash 3d3263e0d872, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

craft 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 10d 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.

skills/seedcraft/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SeedCraft

Converts Claude Code usage statistics into a Minecraft world seed with real biome correlation — the generated world's spawn biome genuinely reflects your coding behavior.

Web companion: seedcraft.dev — browse the community gallery, explore biome tiers, and share your world.

How it works

  1. Reads session data from ~/.claude/projects/ (JSONL conversation files)
  2. Extracts rich stats: messages, tool calls by category, session durations, project count, write/edit volume, error rates, agent usage, and more
  3. Maps stats to a Minecraft climate profile:
    • More messages = hotter world (Temperature)
    • More tool calls = lusher vegetation (Humidity)
    • Longer total session time = taller mountains (Elevation/Erosion)
    • More projects = more biome diversity
    • More write/edit calls = more continental (less ocean)
    • More unique tools = weirder terrain
    • More agent calls = more structures/villages
  4. Calls the SeedCraft API (seedcraft.dev) for matching against 500,000 curated seeds. If the API is unreachable, falls back to a local database of 7,090 seeds. Uses two-stage biome selection: first finds the correct biome, then the best individual seed within that biome
  5. Outputs the seed, a visual climate card, and a biome-specific narrative

Usage

Steps

  1. If the user's intent is NOT already clear, use AskUserQuestion to ask what they want:

    Question: "What Minecraft seed would you like to generate?" Options:

    • Current project — Seed from your current project ({detect CWD project name})
    • All projects — Seed combining all your Claude Code activity
    • Unique seed — 100% unique seed hashed from your stats (biome is a surprise!)
    • (User can also type a specific project name via "Other")

    Skip this question if the user already specified what they want (e.g. "generate for all", "unique seed", "seed for my-api").

  2. Run the script with --json based on the user's choice:

    node --experimental-strip-types ${CLAUDE_PLUGIN_ROOT}/scripts/generate_seed.ts --json                           # Current project (auto-detect CWD)
    node --experimental-strip-types ${CLAUDE_PLUGIN_ROOT}/scripts/generate_seed.ts --all --json                     # All projects
    node --experimental-strip-types ${CLAUDE_PLUGIN_ROOT}/scripts/generate_seed.ts --all --unique --json            # Unique seed (all)
    node --experimental-strip-types ${CLAUDE_PLUGIN_ROOT}/scripts/generate_seed.ts --unique --json                  # Unique seed (current project)
    node --experimental-strip-types ${CLAUDE_PLUGIN_ROOT}/scripts/generate_seed.ts --project "name" --json          # Specific project
    node --experimental-strip-types ${CLAUDE_PLUGIN_ROOT}/scripts/generate_seed.ts --list                           # List projects
    

    ${CLAUDE_PLUGIN_ROOT} is automatically resolved by Claude Code to the plugin's install directory.

Read the full file on GitHub · 164 lines

Changes

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.

  1. 10d ago First seen · 164 lines · 101 tokens per session scan A 3d3263e0d872

Subscribe to this mod's changes

craft is a skill published in the GitHub repository syaor4n/seedcraft (7 stars, last pushed 5mo ago), licensed MIT. It adds 101 tokens to every session and 1,861 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

minecraft-modpack-server

Host modded Minecraft servers (CurseForge, Modrinth).

NousResearch/hermes-agent · 19 tokens

self-evolve

Capture reusable patterns from a finished project and lift them into framework-level priors (contracts, modules, skeletons) that future projects inherit. Run only when the user explicitly requests self-evolution; the orchestrator executes the workflow.

tettethu/VibeGame · 50 tokens

artist-self-evolve

Distill stable art-generation patterns from a completed project, so future projects produce comparable assets without re-discovering the prompts. Lead-dispatched only — orchestrator invokes this skill from its self-evolve flow with a game-slug message; do not self-trigger.

tettethu/VibeGame · 62 tokens

vibegame-build

Run VibeGame's standard end-to-end game development workflow with reviewer gates. Use when the user wants to create a game from zero or evolve an existing game across multiple stages.

tettethu/VibeGame · 42 tokens

vibegame-start

Resume a VibeGame orchestrator session after vibegame start. Use at the beginning of a Claude or Codex session to inspect team runtime state, repair missing persistent members, load goal and GDD context, inspect tasks, and ask the user what to do next.

tettethu/VibeGame · 61 tokens

vibegame-edit

Iterate broadly on an existing game, on top of vibegame-build. Use when the user asks to change an existing game's art style, genre, or core rules. Not for local tuning such as numbers or game feel. Orchestrator only.

tettethu/VibeGame · 57 tokens