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/jd-solanki/airig/comment-codenpx skills add jd-solanki/airig --skill comment-codegit clone --depth 1 https://github.com/jd-solanki/airigWhat 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 | $0.00100 | $0.02266 |
| Opus 5 | $0.00050 | $0.01133 |
| Sonnet 5 | $0.00020 | $0.00453 |
| Haiku 4.5 | $0.00010 | $0.00227 |
Grade A, and why
comment-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 yesterday.
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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Good Code Comments
Comments exist to capture information that was in the writer's mind but cannot be expressed in the code itself. Code states what happens mechanically; comments supply intent, contracts, rationale, units, invariants, and the higher-level picture. Good comments make a system understandable to someone reading it for the first time and let abstractions hide complexity. The cost is small — typically a fraction of development time — and it pays back every time someone (including the original author, weeks later) needs to read or change the code.
The one rule that governs everything
Comment things that aren't obvious from the code. Before keeping any comment, ask: Could someone who has never seen this code reconstruct this comment just by reading the code next to it? If yes, the comment adds nothing — delete it or replace it with something that does add information. "Obvious" means obvious to a first-time reader, not to you.
This single test eliminates most bad comments and motivates most good ones.
Don't repeat the code
The most common worthless comment simply restates the line below it, at the same level of detail.
i = i + 1 # increment i ← adds nothing
count = len(items) # get the number of items ← adds nothing
A close cousin is the comment that just recycles the words already in the name:
// Obtain a normalized resource name from the request.
String[] getNormalizedResourceName(Request req) { ... }
The only word here not already in the signature is "from." This tells the reader nothing they couldn't read off the declaration. The fix is to use different words than the name, words that explain the meaning the name only hints at: What is a normalized resource name? What are the elements of the returned array? When in doubt, the giveaway is one-comment-per-line at the same granularity as the code.
Comments work at a different level of detail than the code
A comment at the same level as the code repeats it. Useful comments go either lower (more precise) or higher (more abstract) than the code.
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.
- yesterday First seen · 166 lines · 100 tokens per session scan A 0f2b8e095943
comment-code is a skill published in the GitHub repository jd-solanki/airig (2 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 2,266 once invoked, about $0.0005 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…