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.
npx skills add mayor-modder/Cities2-MCP --skill cities2-mod-debugginggit clone --depth 1 https://github.com/mayor-modder/Cities2-MCPWrote 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.
[](https://agentmods.dev/skills/mayor-modder/cities2-mcp/cities2-mod-debugging)<a href="https://agentmods.dev/skills/mayor-modder/cities2-mcp/cities2-mod-debugging"><img src="https://agentmods.dev/badge/skills/mayor-modder/cities2-mcp/cities2-mod-debugging/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.
<a href="https://agentmods.dev/skills/mayor-modder/cities2-mcp/cities2-mod-debugging"><img src="https://agentmods.dev/badge/skills/mayor-modder/cities2-mcp/cities2-mod-debugging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00041 | $0.02136 |
| Opus 5.5 | $0.00016 | $0.00854 |
| Sonnet 5.5 | $0.00008 | $0.00427 |
| Haiku 4.5 | $0.00004 | $0.00214 |
Grade A, and why
cities2-mod-debugging 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cities2 Mod Debugging
Debug CS2 mods with evidence, one focused fix at a time. Use MCP-backed docs for CS2-specific assumptions and record negative constraints that rule out unsafe or misleading shortcuts.
Core principle: Always find root cause before attempting fixes. Plausible source-code guesses are still guesses.
Violating the letter of this process is violating the spirit of debugging.
The Iron Law
NO FIXES WITHOUT ROOT-CAUSE EVIDENCE FIRST
If the failure only appears after the mod is installed, loaded, or run in game, source-code inspection is not enough. Inspect runtime evidence first or state that root cause is unverified and stop before patching.
Debugging Workflow
- State the failing symptom in one sentence: build, package, launch, runtime, UI, save, or gameplay behavior.
- Gather the smallest useful evidence before changing code.
- Classify the failure category and state the likely root cause, or say what remains unknown.
- Form one hypothesis tied to a file, API, asset, package step, or game log entry.
- Apply one focused fix.
- Re-run the narrowest relevant check and compare evidence before/after.
- After applying a fix for runtime, UI, save, or gameplay behavior, either run the relevant build or install check or tell the user exactly why it could not run. Then provide playtesting steps without waiting for the user to ask.
- If the fix fails or the symptom changes, return to evidence and hypothesis instead of stacking unrelated edits.
- After three failed fix attempts, pause and ask whether the architecture, template choice, or modding approach should change.
Runtime And UI Gate
For "build passes but it does not work in game" problems, complete at least one runtime check before editing:
- installed package layout and file timestamps;
- enabled playset/load state;
Modding.log,Unity/Player logs, launch output, or exception stack traces;- UI debugger state at
localhost:9444for UI mods.
Source files, package.json, and dist/ui.js can support a hypothesis, but
they do not prove why an installed CS2 mod failed at runtime. If those are the
only facts available, hand the user a playtesting/log collection step and mark
the root cause unverified. Do not patch a likely selector, import, path, timing,
or binding issue first and ask for logs only if it fails.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 146 lines · 41 tokens per session scan A 332661d49196
cities2-mod-debugging is a skill published in the GitHub repository mayor-modder/Cities2-MCP (10 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 2,136 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 2026-08-31.
Other skills, from other repositories
isuzu-unity-cli
Drive the open Unity Editor from the shell with the isuzu-unity-cli command: console errors, compiling and tests, scenes, GameObjects and components, prefabs, play mode, uGUI clicks, and C# run inside the Editor. SKILL.md gives a command for each common task, so no tool list is needed.
unity-diagnostics
Domain skill — Probe Unity main-thread readiness, inspect persistent jobs, read bounded Console messages, and capture a Play-Mode Game View PNG. Use for install, compile, build, and gameplay verification. Not for clearing logs or arbitrary Editor access.
debug-issue
Systematic Godot debugging decision trees for physics, signals, rendering, navigation, and input issues.
minecraft-debug-mcp
Operate and debug the live Minecraft bot through its built-in MCP REPL server. Use when work requires starting the bot with pnpm dev, connecting to the local MCP endpoint, inspecting cognitive state/logs/history, injecting synthetic chat/events, or running targeted REPL code against the running brain during…
frame-rate
Diagnose and remove FPS caps so the editor and game run uncapped (or at a target FPS). Use when the user says the editor/game is "locked", "capped", or "stuck" at a frame rate (commonly 60 FPS), asks to "unlock"/"uncap"/"raise" FPS, or wants to set a max FPS. Covers t.MaxFPS, VSync, fixed/smoothed frame rate, and…
scenario-unity-gameplay
Use when building or debugging Unity gameplay systems: enemy AI that patrols, chases and attacks, NavMesh baking and agents (AI Navigation 2), feet sliding on agents, state machines or behavior trees, physics projectiles that tunnel, the physics spiral, layers and the collision matrix, CharacterController vs Rigidbody…