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 vaayne/agent-kit --skill lark-cligit clone --depth 1 https://github.com/vaayne/agent-kitWrote 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/vaayne/agent-kit/lark-cli)<a href="https://agentmods.dev/skills/vaayne/agent-kit/lark-cli"><img src="https://agentmods.dev/badge/skills/vaayne/agent-kit/lark-cli/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/vaayne/agent-kit/lark-cli"><img src="https://agentmods.dev/badge/skills/vaayne/agent-kit/lark-cli.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 | $0.00200 | $0.00614 |
| Opus 5.5 | $0.00080 | $0.00246 |
| Sonnet 5.5 | $0.00040 | $0.00123 |
| Haiku 4.5 | $0.00020 | $0.00061 |
Grade A, and why
lark-cli 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.
What it actually says
Lark CLI
lark-cli carries its own agent documentation, compiled into the binary and versioned
with it. Read it from the CLI; do not work from memory and do not look for docs in this
repo.
Routing
lark-cli --help # the 23 domains, one line each
lark-cli <domain> --help # +shortcuts (prefer these) and raw API resources
lark-cli skills read lark-<domain> # the domain guide: concepts, workflows, gotchas
lark-cli skills read lark-<domain> references/<file>.md # deeper references
lark-cli schema <service>.<resource>.<method> # params, types, scopes
Start with lark-cli --help to pick the domain, then read that domain's guide before
the first call. lark-cli api <METHOD> <path> is the escape hatch when no typed command
exists.
Read lark-cli skills read lark-shared first for auth, --as user vs --as bot, and
permission-denied handling. Identity does not carry across commands: pass --as
explicitly on every call in a workflow.
Rules
Every command's --help labels it read, write, or high-risk-write.
high-risk-write requires --yes, and only after the user has confirmed. Use
--dry-run to preview a request without sending it.
--jq <expr> filters JSON output. Suppress the _notice banner that otherwise pollutes
every JSON response:
LARKSUITE_CLI_NO_UPDATE_NOTIFIER=1 LARKSUITE_CLI_NO_SKILLS_NOTIFIER=1 lark-cli ...
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 · 54 lines · 200 tokens per session scan A acd5024026ac
lark-cli is a skill published in the GitHub repository vaayne/agent-kit (53 stars, last pushed 4d ago), licensed MIT. It adds 200 tokens to every session and 614 once invoked, about $0.0008 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
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-wiki
A Feishu/Lark knowledge-base skill for managing knowledge spaces, members, document nodes, and their hierarchy. A knowledge base is an organized collection of linked documents.
lark-note
A Feishu meeting-notes lookup workflow for reading note details and original transcripts when you already have a note ID. Feishu is a collaboration platform that stores meeting records and documents.
sheets
Read and query Lark Sheets (spreadsheets) - list sheets in a spreadsheet, read cell data. Use when user asks about a spreadsheet, wants to read data from a Lark sheet, or mentions a spreadsheet URL/ID.