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.
/plugin marketplace add syaor4n/seedcraft/plugin install seedcraftWrote 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/syaor4n/seedcraft/seedcraft)<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.
<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>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 | $0.00101 | $0.01861 |
| Opus 5 | $0.00051 | $0.00931 |
| Sonnet 5 | $0.00020 | $0.00372 |
| Haiku 4.5 | $0.00010 | $0.00186 |
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.
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
- Reads session data from
~/.claude/projects/(JSONL conversation files) - Extracts rich stats: messages, tool calls by category, session durations, project count, write/edit volume, error rates, agent usage, and more
- 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
- 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
- Outputs the seed, a visual climate card, and a biome-specific narrative
Usage
Steps
-
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").
-
Run the script with
--jsonbased 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.
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.
- 10d ago First seen · 164 lines · 101 tokens per session scan A 3d3263e0d872
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.
Other skills, from other repositories
minecraft-modpack-server
Host modded Minecraft servers (CurseForge, Modrinth).
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.
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.
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.
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.
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.