unbanished: Skill for Claude Code

.agents/skills/banished-land/SKILL.md

banished-land is a skill for Claude Code, Codex from tanepiper/unbanished. It costs 74 tokens per session (886 once invoked), scanned A, original, Apache-2.0.

A workflow for documenting Banished reverse-engineering and porting work, then safely recording those changes in Git, a system for tracking code history. It also keeps the project's checklist and status up to date.

In plain words
What is it for?
Use it after tracing game behaviour, decoding a file format, or porting a feature to write evidence-based documents, update the project checklist, and commit only the intended files.
Why use it?
It prevents findings from being lost or presented as facts when they are only guesses. It reduces the risk of committing original game files, temporary analysis files, or changes made by another work session.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

This is tanepiper/unbanished's own configuration. It tells Claude Code and Codex how to work on unbanished itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything unbanished configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tanepiper/unbanished. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tanepiper/unbanished/main/.agents/skills/banished-land/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/tanepiper/unbanished

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 banished-land

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/tanepiper/unbanished/banished-land"><img src="https://agentmods.dev/badge/skills/tanepiper/unbanished/banished-land.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 886 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 $0.00074 $0.00886
Opus 5.5 $0.00030 $0.00354
Sonnet 5.5 $0.00015 $0.00177
Haiku 4.5 $0.00007 $0.00089

Measured 3d ago against content hash 249ac5e7c41a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

banished-land 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.

.agents/skills/banished-land/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Document, commit and push

1. Document

  • Where: extend the topic doc if one exists (grep -rln <address|resource> docs/); otherwise create docs/<TOPIC-IN-CAPS>.md. Sequential game-loop traces continue as docs/GAME-LOOP-STEP-NN.md (next free number) and are linked from the checklist.
  • Style (match existing docs):
    • opening paragraph: what this covers, binary/build, evidence type (static Ghidra 12.1.4 pseudocode, disassembly, emulation, decoded resources) and what was not observed;
    • prose and tables keyed by function address (FUN_1400be770) and field offsets (+0x44);
    • every claim is observed, inferred (say so), or listed under Open questions;
    • links to related docs; no copied pseudocode, disassembly or resource dumps.
  • Checklist: tick or add items in docs/GAME-LOOP-CHECKLIST.md (both "reverse-engineering" and "port" sections) and bump its Updated date. Update README.md status/crate table if a new capability or command exists.

2. Check what you are about to commit

git status --short
git diff --stat

Never stage: anything under game-data/ or analysis/, *.pkg *.crs *.rsc *.str *.sav *.exe *.dll, .venv/, target/, dist/, PNG captures, emulator dumps, shader disassembly. .gitignore covers most — don't force-add (-f) past it.

3. Stage only your own work (concurrent sessions)

Other sessions edit this repo at the same time. Never git add -A / git add . / git commit -a.

  • Whole files you own: git add path/one path/two.
  • A shared file with someone else's unrelated edits: stage only your hunks. Non-interactive way — build the staged version and write it straight into the index:
    git show HEAD:apps/game/src/main.rs > "$TMP/main.rs"   # then apply only your edits to it
    blob=$(git hash-object -w "$TMP/main.rs")
    git update-index --cacheinfo 100644,$blob,apps/game/src/main.rs
    
    (git add -p is interactive and unavailable.) If your change can't be separated, ask before committing someone else's work.
  • git diff --cached --stat to confirm, and make sure the staged tree builds if you split hunks (git stash --keep-index is unsafe with concurrent writers — prefer building a worktree: git worktree add "$TMP/check" HEAD then apply git diff --cached there and cargo check).

Read the full file on GitHub · 72 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. 3d ago First seen · 72 lines · 74 tokens per session scan A 249ac5e7c41a

Subscribe to this mod's changes

banished-land is a skill published in the GitHub repository tanepiper/unbanished (23 stars, last pushed 22d ago), licensed Apache-2.0. It adds 74 tokens to every session and 886 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-11-15.

Related

banished-land compared with skills from other repositories

banished-land next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
banished-landtanepiper/unbanishedSkill2322d agoApache-2.0A74Claude Code, Codex
pr-creationheristop/leclapSkill3517d agoMITA50Claude Code, Codex
create-prprisma/ormSkill48ktodayApache-2.0A47Claude Code, Codex
git-commitThinkInAIXYZ/deepchatSkill6.4ktodayApache-2.0A15Claude Code, Codex
engineer-bot-opsmakecindy/cindySkill10ktodayApache-2.0A57Claude Code, Codex
mcore-split-prNVIDIA/skillsSkill4.1ktodayApache-2.0A25Claude Code
contributingHugoRCD/evlogSkill1.9k3d agoMITA68Claude Code, Codex