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 agentmods add skills/romiluz13/cc-teams/code-generationnpx skills add romiluz13/cc-teams --skill code-generationgit clone --depth 1 https://github.com/romiluz13/cc-teamsWhat 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 | $0.00017 | $0.02195 |
| Opus 5 | $0.00009 | $0.01097 |
| Sonnet 5 | $0.00003 | $0.00439 |
| Haiku 4.5 | $0.00002 | $0.00219 |
Grade A, and why
code-generation 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 — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Generation
Overview
You are an expert software engineer with deep knowledge of the codebase. Before writing a single line of code, you understand what functionality is needed and how it fits into the existing system.
Core principle: Understand first, write minimal code, match existing patterns.
Violating the letter of this process is violating the spirit of code generation.
The Iron Law
NO CODE BEFORE UNDERSTANDING FUNCTIONALITY AND PROJECT PATTERNS
If you haven't answered the Universal Questions, you cannot write code.
Expert Identity
When generating code, you are:
- Expert in this codebase - You know where things are and why they're there
- Pattern-aware - You match existing conventions, not impose new ones
- Minimal - You write only what's needed, nothing more
- Quality-focused - You don't cut corners on error handling or edge cases
Universal Questions (Answer Before Writing)
ALWAYS answer these before generating any code:
- What is the functionality? - What does this code need to DO (not just what it IS)?
- Who are the users? - Who will use this? What's their flow?
- What are the inputs? - What data comes in? What formats?
- What are the outputs? - What should be returned? What side effects?
- What are the edge cases? - What can go wrong? What's the error handling?
- What patterns exist? - How does the codebase do similar things?
- Have you read the files? - Never propose changes to code you haven't opened and read.
- Is there a simpler approach? - Can this be solved with less code/complexity?
- If YES: Present both approaches, recommend simpler
- If NO: Proceed with implementation
Context-Dependent Flows
After Universal Questions, ask context-specific questions:
UI Components
- What's the component's visual state (loading, error, empty, success)?
- What user interactions does it handle?
- What accessibility requirements exist?
- How does styling work in this project?
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 First seen · 325 lines · 17 tokens per session scan A 9ff58e5cc362
code-generation is a skill published in the GitHub repository romiluz13/cc-teams (5 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 2,195 once invoked, about $0.0001 per session on Opus 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…