safe-mining

safe-mining is a skill for Claude Code, Codex from flamingrickpat/pm-minecraft. It costs 59 tokens per session (541 once invoked), scanned A, original, MIT.

A set of rules for safely moving vertically and mining in Minecraft. It tells a bot to use walkable staircases, choose the right tool, and avoid straight shafts.

In plain words
What is it for?
Use it when an agent must descend into a mine, climb out, mine blocks, or choose an inventory tool safely.
Why use it?
It prevents the bot from getting trapped or falling into hazards such as lava, water, or bedrock, and avoids mining with the wrong tool.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/flamingrickpat/pm-minecraft/safe_mining
Any agent
npx skills add flamingrickpat/pm-minecraft --skill safe_mining
Clone the repo
git clone --depth 1 https://github.com/flamingrickpat/pm-minecraft

Made for: Claude Code, Codex.

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 safe-mining

README.md
[![agentmods](https://agentmods.dev/badge/skills/flamingrickpat/pm-minecraft/safe_mining.svg)](https://agentmods.dev/skills/flamingrickpat/pm-minecraft/safe_mining)
Your own site
<a href="https://agentmods.dev/skills/flamingrickpat/pm-minecraft/safe_mining"><img src="https://agentmods.dev/badge/skills/flamingrickpat/pm-minecraft/safe_mining.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 541 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00059 $0.00541
Opus 5 $0.00030 $0.00270
Sonnet 5 $0.00012 $0.00108
Haiku 4.5 $0.00006 $0.00054

Measured 3d ago against content hash 16fdfd7d6997, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

safe-mining 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 3d 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.

deploy/agent_skills/safe_mining/SKILL.md · 45 lines

What it actually says

Safe Mining & Vertical Travel

The most common way to break a run is a vertical move the bot can't undo: a straight shaft is a one-way trip.

Never dig straight down or straight up

  • Legacy skills descend.ts and descend_to_depth.ts throw a loud error on purpose — they carved 1-wide straight shafts. Do not use them.
  • A straight shaft cannot be climbed back out and can drop you into undetectable lava/water/bedrock.

Do this instead

  • Going down: staircase_down (or dig_staircase) carves a 1-wide, 2-tall ramp you can walk down AND back up. Set targetY to your depth goal.
  • Going up / out of a mine: staircase_up clears the headroom (the two cells above your head) then climbs one level at a time — works in the low-ceiling tunnels where pillar_up fails for lack of headroom.
  • minecraft_pillar_up is fine outdoors / in open space only, where there is headroom. It needs a placeable solid block in hand.

Equip the right tool first

  • Call minecraft_inventory_slots to see the current slot layout: an index -> {name} map plus heldItem/heldSlot. This tells you exactly what is in your hands and which slot it is in — never guess.
  • Before mining, minecraft_equip a matching tool (*_pickaxe for stone/ore, *_axe for wood, *_shovel for dirt/gravel). A steel pickaxe still can't harvest stone if you're holding cobblestone.
  • If a mine_block returns unharvestable, equip the correct tool from the slot map and retry.

Watch the furnace

  • Smelting re-uses whatever furnace is nearby. The fix clears stale input/fuel and only collects output when your inventory can hold it.
  • If a smelt returns inventory_full_for_output, free a slot first, then smelt again to collect — the bars are still in the furnace, not lost.
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. 3d ago First seen · 45 lines · 59 tokens per session scan A 16fdfd7d6997

Subscribe to this mod's changes

safe-mining is a skill published in the GitHub repository flamingrickpat/pm-minecraft (1 stars, last pushed 12d ago), licensed MIT. It adds 59 tokens to every session and 541 once invoked, about $0.0003 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens