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 CometWorks/skills --skill se-dev-scriptgit clone --depth 1 https://github.com/CometWorks/skillsWrote 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/cometworks/skills/se-dev-script)<a href="https://agentmods.dev/skills/cometworks/skills/se-dev-script"><img src="https://agentmods.dev/badge/skills/cometworks/skills/se-dev-script/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/cometworks/skills/se-dev-script"><img src="https://agentmods.dev/badge/skills/cometworks/skills/se-dev-script.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00031 | $0.01753 |
| Opus 5.5 | $0.00012 | $0.00701 |
| Sonnet 5.5 | $0.00006 | $0.00351 |
| Haiku 4.5 | $0.00003 | $0.00175 |
Grade A, and why
se-dev-script 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 2d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SE Dev Script Skill
In-game (programmable block, aka PB) script development for Space Engineers version 1.
⚠️ CRITICAL: Commands run in UNIX shell. Use bash syntax. On Windows this is BusyBox; on Linux use native shell.
Examples:
- ✅
test -f file.txt && echo exists - ✅
ls -la | head -10 - ❌
if exist file.txt (echo exists)- Will NOT work
Actions:
- prepare: Run one-time preparation (
Prepare.baton Windows,prepare.shon Linux) - bash: Run UNIX shell commands via busybox
- search: Search script code using
search_scripts.py
Routing Decision
Check these patterns in order - first match wins:
| Priority | Pattern | Example | Route |
|---|---|---|---|
| 1 | Empty or bare invocation | se-dev-script |
Show this help |
| 2 | Prepare keywords | se-dev-script prepare, se-dev-script setup, se-dev-script init |
prepare |
| 3 | Bash/shell keywords | se-dev-script bash, se-dev-script grep, se-dev-script cat |
bash |
| 4 | Search keywords | se-dev-script search, se-dev-script find class, se-dev-script lookup |
search |
Getting Started
⚠️ CRITICAL: Before running ANY commands, read CommandExecution.md to avoid common mistakes that cause command failures.
If Prepare.DONE file missing in this folder, you MUST run one-time preparation steps first. See the prepare action.
Essential Documentation
- CommandExecution.md - ⚠️ READ THIS FIRST - Windows command execution details; on Linux keep bash syntax and use
prepare.sh
Script Development
Use only names matching the PB API whitelist: PBApiWhitelist.txt
Whitelist was exported from game version 1.208.015 using MDK2's Mdk.Extractor.
In-game (PB) scripts released on Steam Workshop or Mod.IO, mostly on former. In-game scripts compiled by game on loading into PB or world loading (if PB has script loaded) with PB Script API whitelist enforced, which guarantees safety and security. Scripts cannot crash game, since any exception caught and script killed by game. Scripts can still lag game if no specific resource usage enforcement set up by player or server admin.
What ships with it
27 files 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.
- .python-version 5 B
- actions/bash.md 1.9 KB
- actions/prepare.md 2.6 KB
- actions/search.md 2.7 KB
- Clean.bat 591 B runs code
- clean.sh 506 B runs code
- CommandExecution.md 866 B
- CommandExecutionDetails.md 7.1 KB
- common-posix.sh 7.5 KB runs code
- cs_indexer.py 38 KB runs code
- hierarchy_tree.py 2.6 KB runs code
- index_scripts.py 19 KB runs code
- list_scripts.py 2.9 KB runs code
- PBApiWhitelist.txt 18 KB
- Prepare.bat 2.7 KB runs code
- Prepare.md 1.3 KB
- prepare.sh 1.3 KB runs code
- pyproject.toml 388 B
- script_paths.py 2.8 KB runs code
- ScriptDev.md 1.5 KB
- ScriptMerge.md 5.0 KB
- ScriptTemplate.md 2.8 KB
- search_scripts.py 17 KB runs code
- summarize_whitelist.py 777 B runs code
- Troubleshooting.md 5.5 KB
- UtilityScripts.md 64 B
- uv.lock 79 KB
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.
- 2d ago Changed · -1 lines 0bd6d374ce6e
- 29d ago Changed · +1 lines 4cae17293fc5
- 1mo ago First seen · 138 lines · 31 tokens per session scan A 088c906c6a8d
se-dev-script is a skill published in the GitHub repository CometWorks/skills (10 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 1,753 once invoked, about $0.0001 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
gdextension
Use when building native extensions for Godot — godot-cpp (C++) or gdext (Rust), binding classes, building, and GDScript/C# interop.
game-development
Expert guidance for game development with C#/Unity, Lua scripting, and best practices for scalable game architecture.
unity-csharp
A set of practical guidelines for writing Unity game scripts in C#. Unity is a game engine, and these rules cover its update loop, object lifetime, memory cleanup, coroutines, and editable data.
script-execute
Compiles and runs C# in the Unity Editor (Roslyn): plain statements with the last expression as the result, or a full class with a static method. See the skill body for the modes, usings/include and Unity object parameters.
godot-csharp
Use C#/.NET in Godot 4.7: partial classes extending nodes, the PascalCase lifecycle (Ready/Process/PhysicsProcess), [Export] fields, [Signal] delegates as C# events, type-safe node lookup, and calling between C# and GDScript. Use when writing Godot game code in C# (.cs files, .csproj), needing the Godot .NET build…
script-read
Read a .cs script file and return its content as a string. Supports a 1-based lineFrom/lineTo slice for partial reads. Pair with 'script-update-or-create' to write back.