unbanished: Skill for Claude Code

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

banished-verify is a skill for Claude Code, Codex from tanepiper/unbanished. It costs 59 tokens per session (760 once invoked), scanned A, original, Apache-2.0.

A verification workflow for the Banished reimplementation, covering automated Rust tests, scripted game launches, screenshots, and the WebAssembly build. WebAssembly is a format that lets code run in browsers and other environments.

In plain words
What is it for?
Use it after changing a port, file-format parser, or shader to test the workspace, inspect headless game scenes, check scripted controls, and verify the browser build.
Why use it?
It checks more than whether the code compiles: it helps confirm behaviour through test results and visible game captures. It also explains how to handle tests that need the user's game data.

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-verify/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-verify

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/tanepiper/unbanished/banished-verify"><img src="https://agentmods.dev/badge/skills/tanepiper/unbanished/banished-verify.svg" alt="Reviewed on agentmods" width="80" 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 760 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 $0.00059 $0.00760
Opus 5.5 $0.00024 $0.00304
Sonnet 5.5 $0.00012 $0.00152
Haiku 4.5 $0.00006 $0.00076

Measured 3d ago against content hash 6ce1f3eb57ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

banished-verify 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-verify/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify a change

Prefer evidence you can look at: a test result or a PNG you have opened with the Read tool. Never report "works" from a build alone.

Tests

cargo test --release                                   # whole workspace
cargo test --release -p unbanished-formats --test toolbar
cargo test --release -p unbanished-game --test terrain_emu

Tests that need game-data/ print a skip message and pass when it is missing — check the output actually ran the assertions (look for the skip text) before claiming coverage.

Headless captures of the game (unbanished = unbanished-app)

Captures go to game-data/derived/captures/ (git-ignored); open them with Read to inspect.

# Boot flow: splash → loading → menu, capture at T seconds
cargo run --release -p unbanished-app -- --boot-capture game-data/derived/captures/menu.png 4.5
UNBANISHED_MENU_SCENE=3 cargo run --release -p unbanished-app -- --boot-capture …/scene3.png 4.5

# Into a new game: press named UI elements at times (repeatable --press NAME@T)
cargo run --release -p unbanished-app -- --boot-capture …/game.png 9 \
  --press [email protected] --press [email protected]

# Map only, with generation options
cargo run --release -p unbanished-app -- --capture …/map.png --view overview|ground \
  --seed 290 --terrain Valleys --size 0 --month 6

--press warns not found at T s if the element name doesn't exist at that moment — treat that as a failure, not noise. Element names come from the dialog resource (dialog_info example). To test a toolbar/sub-menu, chain presses by element name with ~0.3 s gaps after the game loop's fade.

Viewer

cargo run --release -p unbanished-viewer -- --screenshot game-data/derived/captures/d.png dialogs MainMenu_resource

Web (WASM)

cargo build --release -p unbanished-app --target wasm32-unknown-unknown   # compile check
tools/dev-web.sh --app game --release     # serves http://127.0.0.1:8733/?data=/game-data/

For an interactive check, open that URL in the built-in browser pane (launch config game-web) and read the console for errors. Audio only starts after the first click (browser gesture rule). The pane's emulated viewport can size the canvas oddly; real browsers are fine — don't chase it.

Read the full file on GitHub · 69 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 · 69 lines · 59 tokens per session scan A 6ce1f3eb57ee

Subscribe to this mod's changes

banished-verify is a skill published in the GitHub repository tanepiper/unbanished (23 stars, last pushed 22d ago), licensed Apache-2.0. It adds 59 tokens to every session and 760 once invoked, about $0.0002 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-verify compared with skills from other repositories

banished-verify next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
banished-verifytanepiper/unbanishedSkill2322d agoApache-2.0A59Claude Code, Codex
hearth-playtestechoo19/hearthSkill431mo agoMITA112Claude Code
test-playable-web-gamesMengTo/SkillsSkill7.7ktodayMITA52Codex
soundclawiamlukethedev/Claw3DSkill2.5k14d agoMITA18Claude Code, Codex
task-manageriamlukethedev/Claw3DSkill2.5k14d agoMITA56Claude Code, Codex
todoiamlukethedev/Claw3DSkill2.5k14d agoMITA12Claude Code, Codex
godot-e2evalkor-ai/loomSkill1.5k8d agoApache-2.0A189Claude Code