unbanished: Skill for Claude Code

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

banished-port is a skill for Claude Code, Codex from tanepiper/unbanished. It costs 80 tokens per session (1,072 once invoked), scanned A, original, Apache-2.0.

A guide for transferring behaviour found in the original Banished program into the Rust reimplementation. It covers game logic, file parsing, user-interface controls, engine loops, and rendering code.

In plain words
What is it for?
Use it when implementing a feature that has already been traced and whose required resources can already be read, such as tools, status displays, placement, calendars, and rendering.
Why use it?
It prevents developers from inventing behaviour before understanding the original. It also gives each kind of change a suitable place in the project and requires tests or evidence for matching results.

Skill for Claude CodeCodex

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

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-port/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-port

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/tanepiper/unbanished/banished-port"><img src="https://agentmods.dev/badge/skills/tanepiper/unbanished/banished-port.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,072 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 $0.00080 $0.01072
Opus 5.5 $0.00032 $0.00429
Sonnet 5.5 $0.00016 $0.00214
Haiku 4.5 $0.00008 $0.00107

Measured 3d ago against content hash 97e561dbdee3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

banished-port 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-port/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Port to Rust, 1:1

Precondition: the behaviour is traced (banished-trace) and any resource it reads parses (banished-format). If you find yourself inventing behaviour, stop and trace it.

Where code goes

Kind Location Constraints
Deterministic game logic, simulation, generators, queries crates/game No wgpu/winit/audio; bit-exact where emulated; unit/parity tests
Resource parsing crates/formats Dependency-free
UI element tree, controls, layout, input, events crates/ui Generic engine UI — no Banished-specific game rules
Engine loops, game controllers, dialog controllers, input routing apps/game/src/*.rs One module per original controller (toolbar.rs, status_bar.rs, …)
Rendering apps/game/src/gfx/render/, gfx/models.rs + gfx/models/ (models.wgsl), *.wgsl Must run on WebGL2 too (see banished-shader)

Mirror the original's shape

  • Name modules/structs after the original classes or resources (ToolbarItem, GameplayLoop), and put the original address on each ported function: /// Port of FUN_1400be680 (speed step): speeds 1, 2, 5, 10.
  • Keep the original's data flow: if the original builds a dialog from Dialog/X.rsc and fills it from resources, do the same — don't hand-build UI that the game ships as a resource.
  • Keep constants with their source address; don't "tidy" magic numbers into different values.
  • Mark deliberate deviations (platform differences, WebGL limits, threads → incremental steps) with // Deviation: and a reason.

Engine loop model (apps/game/src/loops.rs)

MainLoop runs one loop at a time; LoaderLoop/DialogLoaderLoop load the next loop incrementally (no threads — the web can't block). Fades run at 4 units/s. A loop owns a Screen: add_dialog(ui, "Dialog/X.rsc:resource"), add_modal, remove_dialog, find(name), layout, input_root. The game loop is GameplayLoop in gameplay.rs (built by FUN_14009d530, UI installed by FUN_14009d0d0: Toolbar, EventNotify, AutoSave).

Read the full file on GitHub · 67 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 · 67 lines · 80 tokens per session scan A 97e561dbdee3

Subscribe to this mod's changes

banished-port is a skill published in the GitHub repository tanepiper/unbanished (23 stars, last pushed 22d ago), licensed Apache-2.0. It adds 80 tokens to every session and 1,072 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-port compared with skills from other repositories

banished-port next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
banished-porttanepiper/unbanishedSkill2322d agoApache-2.0A80Claude Code, Codex
soundclawiamlukethedev/Claw3DSkill2.5k14d agoMITA18Claude Code, Codex
task-manageriamlukethedev/Claw3DSkill2.5k14d agoMITA56Claude Code, Codex
todoiamlukethedev/Claw3DSkill2.5k14d agoMITA12Claude Code, Codex
gamedev-shippingericrisco/rsc-harnessSkill636todayMITA99Claude Code, Codex
self-evolvetettethu/VibeGameSkill38810d agoApache-2.0A50Claude Code, Codex
artist-self-evolvetettethu/VibeGameSkill38810d agoApache-2.0A62Claude Code, Codex