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/mickeyyaya/refactoring-skills/code-documentation-patternsnpx skills add mickeyyaya/refactoring-skills --skill code-documentation-patternsgit clone --depth 1 https://github.com/mickeyyaya/refactoring-skillsWhat 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 | $0.00068 | $0.05072 |
| Opus 5 | $0.00034 | $0.02536 |
| Sonnet 5 | $0.00014 | $0.01014 |
| Haiku 4.5 | $0.00007 | $0.00507 |
Grade A, and why
code-documentation-patterns 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.
How it starts
The opening of the file, as written. The whole thing — 546 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Documentation Patterns
Overview
Stale docs erode trust, misleading comments introduce bugs, and undocumented architectural decisions get re-litigated every six months. Use this guide to write documentation that stays accurate, helps future contributors, and scales with the codebase.
When to use: Adding a new public API, recording an architectural decision, onboarding a new team member, reviewing PRs for documentation completeness, or auditing a codebase for documentation health.
Quick Reference
| Pattern | Core Idea | Primary Red Flag |
|---|---|---|
| Architecture Decision Record | Document context, decision, and consequence in a lightweight file | Decision made verbally, never written down; team re-debates the same choice |
| API Documentation (OpenAPI/AsyncAPI) | Machine-readable contract that doubles as human-readable reference | Docs generated from code only, never from intent; drifts from actual behavior |
| JSDoc / Docstrings | Inline structured comments on public interfaces | Missing param types, stale return descriptions, no examples for complex behavior |
| README Standards | Orientation doc covering purpose, setup, usage, and runbook | README last updated two major versions ago; no local-run instructions |
| Inline Documentation | Explain why, not what; annotate non-obvious decisions | Comments restate the code; intent buried; nothing explains the workaround |
| Technical Debt Register | Intentional debt tracked with owner, cost, and due date | // TODO comments with no date, owner, or ticket reference |
| Documentation Anti-Patterns | Stale docs, misleading comments, commented-out code | Committed code blocks that "might be useful later" |
Patterns in Detail
1. Architecture Decision Records (ADR)
An ADR captures the context, decision, and consequence of a significant technical choice. It is the single artifact that prevents a future engineer from re-opening a settled debate without understanding why it was settled.
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.
- 3d ago First seen · 546 lines · 68 tokens per session scan A 7f21221f7f4b
code-documentation-patterns is a skill published in the GitHub repository mickeyyaya/refactoring-skills (6 stars, last pushed 5mo ago), licensed MIT. It adds 68 tokens to every session and 5,072 once invoked, about $0.0003 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…