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/mr-tbot/auto-everything/auto-commentnpx skills add mr-tbot/Auto-Everything --skill auto-commentgit clone --depth 1 https://github.com/mr-tbot/Auto-EverythingWhat 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 | $0.00087 | $0.02466 |
| Opus 5 | $0.00044 | $0.01233 |
| Sonnet 5 | $0.00017 | $0.00493 |
| Haiku 4.5 | $0.00009 | $0.00247 |
Grade A, and why
auto-comment 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/auto-comment
Bring the codebase's comments into line with what the code actually does — incrementally, resumably, and without touching the comments that are load-bearing.
The failure this exists for: successive passes by different hands and different models. One adds a comment to every line, one strips comments as noise, one writes none. What is left is a codebase where comment density signals nothing about complexity and half the comments describe code that has since changed.
A comment that lies is worse than no comment, because it is trusted. Stale comments are the primary target of this skill; missing ones are secondary.
Step 1 — Read Your Own State
State lives in .agent/comment-state.json (create it if absent, and make sure it is gitignored or
committed deliberately — either is fine, but decide):
{
"last_run": "2026-08-17T14:22:05Z",
"last_commit": "f932834…",
"conventions": { "…": "what was established in step 2" },
"swept": ["src/core/", "src/api/"],
"remaining": ["src/legacy/", "src/vendor-shim/"],
"deliberate_skips": { "src/generated/": "codegen output, never edit" }
}
On every run:
- No state file → this is a first run. Go to Step 2 and establish conventions.
- State exists → compute what changed since
last_commit:
git diff --name-only <last_commit>..HEAD
git log --oneline <last_commit>..HEAD | head -20
Then work in this order:
- Changed files first. Code that moved is where comments went stale. This is the highest-value work and it is what "keep comments in line with the codebase" actually means.
- Then the backlog — the next slice of
remaining, so an untouched corner eventually gets swept. - Update state at the end of every run, including a partial one. A run that does not update state has broken the resumability that justifies the skill.
Report at the start: when you last ran, how many commits ago, and what you are covering this run.
Step 2 — Establish The Convention, Do Not Impose One
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 · 203 lines · 87 tokens per session scan A 41bbfe128bff
auto-comment is a skill published in the GitHub repository mr-tbot/Auto-Everything (5 stars, last pushed 8d ago), licensed MIT. It adds 87 tokens to every session and 2,466 once invoked, about $0.0004 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…