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 Haili321/haili-auto-mkt --skill phgit clone --depth 1 https://github.com/Haili321/haili-auto-mktWrote 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/haili321/haili-auto-mkt/ph)<a href="https://agentmods.dev/skills/haili321/haili-auto-mkt/ph"><img src="https://agentmods.dev/badge/skills/haili321/haili-auto-mkt/ph/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/haili321/haili-auto-mkt/ph"><img src="https://agentmods.dev/badge/skills/haili321/haili-auto-mkt/ph.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00061 | $0.00812 |
| Opus 5 | $0.00030 | $0.00406 |
| Sonnet 5 | $0.00012 | $0.00162 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
ph 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Hunt Daily
Use this skill once a day to keep a Product Hunt account active without looking spammy. The script reads the day's leaderboard via the PH GraphQL API, groups posts by primary topic, and suggests upvote targets spread across topics.
The goal is account warming, not vote manipulation: a real human still opens the suggested links, reads, and chooses what to actually upvote or comment. The script does not call any write endpoints.
Boundary
- Never commit
.ph_tokens.json. It's gitignored. - The script only reads. Upvoting and commenting stay manual.
- One PH account, one cadence. Do not run this on multiple accounts in a single day from the same IP; PH treats coordinated voting harshly.
Daily cadence (the actual warming routine)
The "warming" part isn't the script; it's the habit. The script just makes the habit cheap to run.
- Run
python3 scripts/ph_daily.pyin the morning. Read the digest. - Pick 5 to 8 products across different topics. Cross-topic matters more than vote count; voting only on AI products every day flags the account.
- Open each product page on producthunt.com. Spend 20+ seconds reading the tagline and first comment. PH tracks dwell time per session.
- Upvote the ones you'd actually try. Skip the ones you wouldn't; an account that upvotes everything looks fake.
- Optionally leave one short, substantive comment on the product you find most interesting that day. Two sentences. No links. No promotion.
- Close the tab. Do not loop.
Skip days are fine; long streaks of activity look more bot-like than an honest weekly rhythm.
Entry points
Today's leaderboard, human-readable digest:
python3 skills/ph/scripts/ph_daily.py
Specific date (UTC; PH closes boards on Pacific time, so very recent dates may be empty):
python3 skills/ph/scripts/ph_daily.py 2026-05-18
Machine-readable JSON for piping into other tools:
python3 skills/ph/scripts/ph_daily.py --json
Suggest a different number of cross-topic picks:
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 105 lines · 61 tokens per session scan A 68b252b11bde
ph is a skill published in the GitHub repository Haili321/haili-auto-mkt (2 stars, last pushed 3mo ago), licensed MIT. It adds 61 tokens to every session and 812 once invoked, about $0.0003 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
larksnap-fetch
A bridge for downloading Feishu/Lark documents or ordinary webpages into local files, with options such as Markdown, HTML, or PDF. Feishu, also called Lark, is a workplace collaboration platform.
lark-cli
A command-line tool for working with Lark, also called Feishu, a workplace collaboration platform. It covers services such as calendars, meetings, documents, spreadsheets, messaging, tasks, approvals, and shared files.
cherry-studio-design-language
A design system and template library for creating Cherry Studio presentations and other visual materials. It defines reusable page layouts, spacing, typography, icons, and visual rules.
3080-brief
Create a new source-grounded decision brief in the source format by default (Feishu/Lark, Word/docx, Markdown, or self-contained HTML) with a reader-fit Pyramid opening, one editable or auditable visual covering at least 80% of value-weighted non-appendix claims, and one key-question table. Use when the user names…
lark-sheets
A tool for creating and managing Feishu cloud spreadsheets, including sheets, rows, columns, cells, formulas, charts, pivot tables, filters, and formatting. Feishu is a cloud collaboration platform with spreadsheet features similar to online workbooks.
lark-drive
A Feishu cloud-drive tool for managing online files and folders. Feishu cloud drive is a shared online storage area, similar to Google Drive or Dropbox.