unbanished: Skill for Claude Code

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

banished-trace is a skill for Claude Code, Codex from tanepiper/unbanished. It costs 84 tokens per session (1,602 once invoked), scanned A, original, Apache-2.0.

A guide for examining the original Banished program without running it, using disassembly and decompiled code. It shows how to follow strings, functions, fields, and callers to understand how a feature was implemented.

In plain words
What is it for?
Use it to find a function, field offset, constant, or virtual-method entry related to a game feature before writing a port.
Why use it?
It helps distinguish what the binary directly shows from what has merely been inferred. That reduces the risk of copying an incorrect assumption into the reimplementation.

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-trace/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-trace

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/tanepiper/unbanished/banished-trace"><img src="https://agentmods.dev/badge/skills/tanepiper/unbanished/banished-trace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,602 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 $0.00084 $0.01602
Opus 5.5 $0.00034 $0.00641
Sonnet 5.5 $0.00017 $0.00320
Haiku 4.5 $0.00008 $0.00160

Measured 3d ago against content hash 647a7264dd2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

banished-trace 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-trace/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trace behaviour in the original binary

Static evidence only: never claim the game "does" something at runtime unless it was emulated (banished-emulate) or observed. Label conclusions observed (read in code/data), inferred, or unknown.

0. Check what is already known

grep -rn "FUN_1400be770\|Toolbar" docs/ | head      # address or name
ls analysis/                                        # earlier one-off dumps (local only)

1. Find an entry point

Work outward from something concrete — a resource path, string, type name, or a known caller.

  • Strings → code. Resource paths ("Dialog/Toolbar.rsc"), UI element names ("toolbarContent"), type names. Grep the pseudocode, which inlines string literals:
    D=analysis/export/Application-steam-x64.exe
    grep -n 'Dialog/Toolbar' $D/decomp.c | head
    grep -n 'toolbarContent' $D/strings.txt
    
  • Function by address: each function starts with // ==== <addr> <name>:
    awk '/^\/\/ ==== 1400be770 /{p=1;print;next} /^\/\/ ==== /{p=0} p' $D/decomp.c
    
  • Callers: grep -n 'FUN_1400be770' $D/decomp.c then map line numbers back to the enclosing // ==== header (awk with the last seen header).
  • Engine API: the exe imports Runtime classes by mangled name; Runtime exports are listed in analysis/export/Runtime-steam-x64.dll/exports.txt and named in its decomp.c (e.g. UI::Element::SetChild). Runtime is the place to look for Serialize, UI controls, IO, Math.
  • Resource type IDs: typeId = CRC32(UTF-16LE class name). tools/schema/types.json maps known IDs; python3 tools/schema/typeids.py regenerates it. A serializer for type 0x852ec05b is found by grepping the hex constant in decomp.c (registration tables pair the id with the factory).
  • Vtables: find the table address in a constructor (*param_1 = &PTR_… / 0x14016…), then python3 tools/ghidra/vtable.py game-data/original/Application-steam-x64.exe $D/functions.tsv 0x140165120 40. Engine loop vtables: slot order is the GameLoop interface (load/startup/update/draw/input…); check docs/NEW-GAME-FLOW.md for slots already identified.
  • Constants (DAT_1401xxxxx, float literals Ghidra shows as data refs): python3 tools/ghidra/readdata.py game-data/original/Application-steam-x64.exe f32 0x14016a2b0 0x14016a2b4 (types: f32 f64 i32 u32 hex16).

Read the full file on GitHub · 104 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 · 104 lines · 84 tokens per session scan A 647a7264dd2f

Subscribe to this mod's changes

banished-trace is a skill published in the GitHub repository tanepiper/unbanished (23 stars, last pushed 22d ago), licensed Apache-2.0. It adds 84 tokens to every session and 1,602 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-trace compared with skills from other repositories

banished-trace next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
banished-tracetanepiper/unbanishedSkill2322d agoApache-2.0A84Claude Code, Codex
tune-performanceSummerEngine/summer-engine-agentSkill592mo agoMITA94Claude Code
diagnosing-perf-regressionsSummerEngine/summer-engine-agentSkill592mo agoMITA58Claude Code
debugging-game-feelSummerEngine/summer-engine-agentSkill592mo agoMITA53Claude Code
estella-debuggingesengine/estellaSkill1.2ktodayApache-2.0A55Claude Code, Codex
minecraft-debug-mcpmoeru-ai/airiSkill52ktodayMITA68Codex
performance-optimizationgamedev-skills/awesome-gamedev-agent-skillsSkill9.5k6d agoApache-2.0A97Claude Code