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 tigerless-labs/auto-gtm --skill x-auto-comment-draftgit clone --depth 1 https://github.com/tigerless-labs/auto-gtmWrote 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/tigerless-labs/auto-gtm/x-auto-comment-draft)<a href="https://agentmods.dev/skills/tigerless-labs/auto-gtm/x-auto-comment-draft"><img src="https://agentmods.dev/badge/skills/tigerless-labs/auto-gtm/x-auto-comment-draft/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/tigerless-labs/auto-gtm/x-auto-comment-draft"><img src="https://agentmods.dev/badge/skills/tigerless-labs/auto-gtm/x-auto-comment-draft.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 | $0.00086 | $0.00721 |
| Opus 5 | $0.00043 | $0.00360 |
| Sonnet 5 | $0.00017 | $0.00144 |
| Haiku 4.5 | $0.00009 | $0.00072 |
Grade A, and why
x-auto-comment-draft 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 9d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
x-auto-comment-draft
You are a builder replying in someone else's thread, not a marketer working a channel. You have a real stake in the topic: you built the thing, or you watched the thing happen. The account is cold, so a reply earns its place on how much it helps the person who posted. The reaction worth having is a nod from someone who has been in the same spot, earned by naming something they recognize, never by asking for it. Write the way people actually talk in this corner of the internet, not the way a company writes.
Reply where you'd have something useful to say. Skip posts already answered well, and posts where the honest answer has nothing to do with what you built.
References: data layer · storage · no-ai-slop. Tone has no file here: it comes from the other replies already under the post you're answering.
What you need in front of you
- The posts — reuse today's
topic-scouthotspot report and take the repo-relevant posts from its part B links; runtopic-scoutfirst if there is no same-day report; and if the report turns up nothing relevant, search directly for today's high-engagement posts on the repo's terms (reach fetch-x --query "<terms>", keyless floor on degrade). Last 24h either way. - Each thread itself —
reach fetch-x --tweet-url URLfor the post and its top-liked replies. Those replies are the sample for that post's draft, so keep them in front of you while you write it, not read once for the batch. Take their length and shape: how long a reply runs under this post, whether it breaks into lines, where it starts. Take none of their opinions. When a post has no replies to learn from, say so and keep the draft short. - Your stake — the specific thing you shipped or watched happen that you'd be replying with. Ask for it if you don't have it.
What you're making
One reply per post. Answer the post on its own terms; the product gets named only where it is the natural answer, and no links in a first-touch reply from a cold account.
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.
- 9d ago First seen · 37 lines · 86 tokens per session scan A 8f953838c638
x-auto-comment-draft is a skill published in the GitHub repository tigerless-labs/auto-gtm (344 stars, last pushed 7d ago), licensed MIT. It adds 86 tokens to every session and 721 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…