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/patrickdappollonio/claude-plugins/appropriate-comments-codenpx skills add patrickdappollonio/claude-plugins --skill appropriate-comments-codegit clone --depth 1 https://github.com/patrickdappollonio/claude-pluginsWhat 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 | $0.00174 | $0.07129 |
| Opus 5 | $0.00087 | $0.03564 |
| Sonnet 5 | $0.00035 | $0.01426 |
| Haiku 4.5 | $0.00017 | $0.00713 |
Grade A, and why
appropriate-comments-code 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 — 529 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Appropriate Comments in Code
The Rule
A comment earns its place by carrying information the code does not, about the code as it is now, in as few lines as that takes.
Three ways to fail it, and they are equally fatal:
- Restating the line below it.
- Narrating how the code got here.
- Explaining at length something true and useful — that is documentation, and documentation does not live above a function.
The third is the one people miss. A comment can be entirely accurate, entirely present-tense, free of every ticket number and iteration label, and still be wrong for the spot it occupies.
Overview
A comment describes the code as it is now, for a reader who has none of your context: someone months from now who was not in this session, did not read the pull request, does not know what you tried first, and cannot ask you.
That reader is also skimming. They are looking for one function, and every line above it is a toll they pay to reach it. A comment's cost is not just being wrong later — it is the attention it takes now. Twenty accurate lines above a function is a worse comment than two, because nobody reads twenty.
This skill is language-agnostic. Apply it with whatever comment syntax and documentation convention the project already uses.
When to Use
- Writing any new function, type, module, or test
- Editing code that already has comments above or inside it
- Fixing a bug and feeling the urge to explain the fix in place
- Applying review feedback, whether from a human or from an automated reviewer
- Writing doc comments / docstrings for a public API
- Reviewing someone else's diff that adds comments
- Auditing existing comments in bulk — see Doing this at scale
When NOT to use: the user explicitly asked for annotated, tutorial, or teaching code, where narrating every line is the deliverable. Say that you are setting the skill aside and why.
The Six Tenets
1. Two lines is the working limit
Above a declaration — a function, type, variable, constant, or field — aim for one or two lines. Not as a hard cap, as a forcing function: if you need more, you are usually writing documentation, and it belongs somewhere a reader can find it on purpose.
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 · 529 lines · 174 tokens per session scan A 0d147ee195cc
appropriate-comments-code is a skill published in the GitHub repository patrickdappollonio/claude-plugins (9 stars, last pushed 2d ago), licensed MIT. It adds 174 tokens to every session and 7,129 once invoked, about $0.0009 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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.