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 lark-bloggit 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/lark-blog)<a href="https://agentmods.dev/skills/haili321/haili-auto-mkt/lark-blog"><img src="https://agentmods.dev/badge/skills/haili321/haili-auto-mkt/lark-blog/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/lark-blog"><img src="https://agentmods.dev/badge/skills/haili321/haili-auto-mkt/lark-blog.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 | $0.00073 | $0.01062 |
| Opus 5 | $0.00036 | $0.00531 |
| Sonnet 5 | $0.00015 | $0.00212 |
| Haiku 4.5 | $0.00007 | $0.00106 |
Grade A, and why
lark-blog 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 12d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Markdown blog -> Lark docx
Use this skill to turn a Markdown blog draft (with inline image placeholders) into a reviewable Lark doc. It posts the parsed blocks, then uploads each referenced PNG and binds it to the corresponding image block. The doc you get back is the review handoff; final publish to your company's official website blog is not in scope.
Boundary
- This skill writes a new Lark doc; it never edits the company's official website blog.
- Image uploads use the user OAuth token (from the
larkskill). It will not work with a tenant-only token. Runlark_auth.pyonce first. - The script does not delete or overwrite anything; failed blocks are reported but the rest of the doc still goes through.
Markdown conventions
| Markdown | Becomes |
|---|---|
# Heading |
docx heading1 (block_type 3) |
## Heading |
docx heading2 (block_type 4) |
### Heading |
docx heading3 (block_type 5) |
- bullet |
bullet item (block_type 12) |
```lang...``` |
code block (block_type 14). Recognised langs: python, bash, json. |
> quote |
italic paragraph (block_type 2 + italic style) |
--- |
divider (block_type 22) |
| Markdown table | bullets **header**: value. Lark API tables are awkward; this keeps the doc readable. |
*[image: foo.png | "Caption text"]* |
empty image block (block_type 27) + italic caption paragraph. The image is uploaded and bound after the doc is created. |
Inline: **bold**, *italic*, `code`, [label](https://url).
Entry point
python3 skills/lark-blog/scripts/push_blog_to_lark.py \
--md ./post.md \
--images-dir ./images \
--title 'Post Draft v1'
Optional flags:
--folder-token TOKEN: create the doc inside a specific Lark drive folder instead of at the root.--batch-size N: blocks per create-block API call. Default 40 (Lark's limit is around 50).
Setup
- Install the
larkskill alongside this one and run itslark_auth.pyonce to grant a user token. The script auto-findslark_client.pyin the sibling skill'sscripts/dir. - Override the discovery path with
LARK_CLIENT_PATH=/path/to/lark_scriptsif your install layout differs. - Place your blog Markdown anywhere; pass its path with
--md. - Put referenced PNGs in any folder; pass it with
--images-dir.
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.
- 12d ago First seen · 107 lines · 73 tokens per session scan A d0d75072d9e6
lark-blog is a skill published in the GitHub repository Haili321/haili-auto-mkt (2 stars, last pushed 3mo ago), licensed MIT. It adds 73 tokens to every session and 1,062 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
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.
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.
lark-vc
A Feishu/Lark skill for finding completed video meetings and reading their records, including summaries, action items, chapters, transcripts, and attendee snapshots.
lark-minutes
A Feishu/Lark skill for searching and managing meeting transcription records called Minutes, including summaries, action items, speakers, keywords, and media files.