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 Divide-By-0/autolatex --skill preserve-commentsgit clone --depth 1 https://github.com/Divide-By-0/autolatexWrote 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/divide-by-0/autolatex/preserve-comments)<a href="https://agentmods.dev/skills/divide-by-0/autolatex/preserve-comments"><img src="https://agentmods.dev/badge/skills/divide-by-0/autolatex/preserve-comments/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/divide-by-0/autolatex/preserve-comments"><img src="https://agentmods.dev/badge/skills/divide-by-0/autolatex/preserve-comments.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 | $0.00032 | $0.00812 |
| Opus 5.5 | $0.00013 | $0.00325 |
| Sonnet 5.5 | $0.00006 | $0.00162 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
preserve-comments 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 1mo 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preserve Comments
Existing comments in this codebase are load-bearing context for future agents (and humans). Many describe specific past bugs, race conditions, Apps Script platform quirks, or non-obvious behavior that a casual reader would otherwise "clean up" and re-break. Treat them as part of the source code, not decoration.
Default behavior
- When editing a block, keep all surrounding comments by default. If a comment no longer matches the code, edit it to match — do not delete it.
- When refactoring or moving code, move the comments with it. Do not strip them just because the surrounding shape changed.
- When deleting code, only delete the comments that were specifically about that code. Comments describing nearby invariants, gotchas, or platform behavior stay.
- When adding a workaround, a magic number, or anything non-obvious, add a comment explaining the why — preferably with
// REASON:or// NOTE:prefix so future agents recognize it as intentional context, not noise.
Comments that especially must not be deleted
// REASON:and// NOTE:comments — these are deliberate signals from a past agent or maintainer that the line below is non-obvious.- Comments referencing prior bugs by symptom (e.g., "without this the sidebar reports no equations found", "0x0D vs 0x0A in Docs vs Slides").
- Comments describing Apps Script platform behavior (sandbox modes, AuthMode.LIMITED vs FULL, simple vs installable triggers, library
developmentMode, runtime cache TTLs). - Comments about timing/ordering ("X must happen before Y because…",
Utilities.sleeprationales). - Comments labeling known-stale or temporary code with cleanup conditions ("remove after Marketplace v8 lands",
@deprecated). - Comments documenting magic numbers, sentinel return values (
-100000,-100001), enum-value-load-bearing notes for cross-fileconst enummirroring.
When in doubt
If you're tempted to delete a comment, ask one of:
- Does this comment describe a behavior that's still true? → keep it as-is.
- Is the behavior true but the wording stale? → edit the comment to match current reality; preserve the underlying detail.
- Is the comment plainly wrong now? → edit to a corrected version; do not silently drop the prior context.
- Is the comment trivially restating the code ("// increment counter")? → safe to drop. But: are you sure it's not subtly disambiguating something? When unsure, keep it.
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.
- 1mo ago First seen · 61 lines · 32 tokens per session scan A 73d31c44571f
preserve-comments is a skill published in the GitHub repository Divide-By-0/autolatex (50 stars, last pushed 21d ago), licensed MIT. It adds 32 tokens to every session and 812 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 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…