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 adbertram/cli-tools --skill tiktok-cligit clone --depth 1 https://github.com/adbertram/cli-toolsWrote 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/adbertram/cli-tools/tiktok-cli)<a href="https://agentmods.dev/skills/adbertram/cli-tools/tiktok-cli"><img src="https://agentmods.dev/badge/skills/adbertram/cli-tools/tiktok-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/adbertram/cli-tools/tiktok-cli"><img src="https://agentmods.dev/badge/skills/adbertram/cli-tools/tiktok-cli.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 | $0.00098 | $0.02479 |
| Opus 5.5 | $0.00039 | $0.00992 |
| Sonnet 5.5 | $0.00020 | $0.00496 |
| Haiku 4.5 | $0.00010 | $0.00248 |
Grade A, and why
tiktok-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 today.
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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<project_overrides> Before acting on this skill, run:
~/.agents/skills/skill-expert/scripts/load-skill-overrides.sh tiktok-cli
Apply any printed instructions alongside this skill's own workflow: they extend it and never repeal its limits. No output means no project override is in effect. A non-zero exit means the project's override file is broken -- report it and stop rather than silently running unmodified. </project_overrides>
<quick_start>
The tiktok CLI follows this pattern:
tiktok <command-group> <action> [arguments] [options]
| Task | Command |
|---|---|
| Download transcripts for one or more TikTok videos. | tiktok transcripts download |
List all of the logged-in account's saved (favorited) TikTok videos. Needs a browser_session login first (tiktok auth login --credential-type browser_session). |
tiktok favorites list |
| Get one saved video's details (id, url, caption, author) by id or URL. No login required. | tiktok favorites get |
| Publish a video through the Content Posting API (custom API profile). | tiktok videos publish |
Check a Direct Post's status by publish_id (custom API profile). |
tiktok videos status |
List a profile's posted videos; your own private posts need your browser_session. |
tiktok videos list |
Get one posted video by id (browser_session). |
tiktok videos get |
| Read verified own-account Studio content with endpoint provenance. | tiktok videos list --profile clipper --username ata_clipper --studio --expected-account-id 7692213003349443597 |
| Read exact owned post IDs in one bounded Studio scan; resume beyond 1000 feed items using caller-owned continuation. | tiktok studio inventory owned-post-ids.json --profile clipper --username ata_clipper --account-id 7692213003349443597 |
| Read actual cumulative views, likes, comments, shares, and favorites for an own post. Missing measurements stay null. | tiktok videos metrics <video_id> --profile clipper --username ata_clipper --expected-account-id 7692213003349443597 |
Read watch time, completion, and retention for 1–1000 own posts in one browser session; a failed post lands in errors and the rest still return. Use instead of one studio watch per post. |
tiktok studio watch-batch post-ids.json --profile clipper --username ata_clipper --account-id 7692213003349443597 |
Permanently delete one of your videos by id; requires --yes (browser_session). |
tiktok videos delete |
Set who can watch one own post (public, friends, private); fails non-zero unless an exact Studio readback shows the requested visibility. |
tiktok videos privacy <video_id> --to public --profile clipper --username ata_clipper --expected-account-id 7692213003349443597 |
| Configure authentication, optionally using a manual browser login. | tiktok auth login |
| Open visible Chrome for manual login in an isolated named browser profile; no stored credentials are submitted. | tiktok auth login --profile clipping --credential-type browser_session --manual |
| Read verified current numeric account ID and username in a named browser profile. | tiktok account get --profile clipping |
| Report each recent own post's restriction state (For You eligibility), TikTok's stated reason, and appeal state; read-only. | tiktok account check --profile clipper --username ata_clipper --expected-account-id 7692213003349443597 |
| Read TikTok Studio's own pre-post verdict (Content check lite, music copyright) for a local MP4; uploads a private draft, removes it, never posts. | tiktok studio check clip.mp4 --profile clipper --username ata_clipper --account-id 7692213003349443597 |
Prepare and publish one MP4 publicly in a single process (owned editor stays open); retries a failed prepare once on a fresh publisher, requires --yes. Read tiktok studio status <request-id> after an error. |
tiktok studio post clip.mp4 --policy policy.json --request-id <uuid> --yes --profile clipper |
| Clear stored credentials. | tiktok auth logout |
Check authentication status across profiles. Performs a live round-trip for every configured credential type so the report reflects ground truth — not on-disk belief. Saved credentials whose live verification fails are reported as authenticated: false with the failure reason in api_test. |
tiktok auth status |
| Manage authentication profiles | tiktok auth profiles |
| </quick_start> |
What ships with it
1 file 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.
- today First seen · 104 lines · 98 tokens per session scan A a384bea3226c
tiktok-cli is a skill published in the GitHub repository adbertram/cli-tools (6 stars, last pushed today), licensed MIT. It adds 98 tokens to every session and 2,479 once invoked, about $0.0004 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 2026-11-07.
tiktok-cli compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tiktok-cliadbertram/cli-tools | Skill | 6 | today | MIT | A | 98 | Claude Code, Codex |
| opencli-autofixjackwener/OpenCLI | Skill | 31k | yesterday | Apache-2.0 | A | 61 | Claude Code |
| open-sourcebrowser-use/browser-use | Skill | 120k | yesterday | MIT | A | 137 | Claude Code |
| opencli-usagejackwener/OpenCLI | Skill | 31k | yesterday | Apache-2.0 | A | 31 | Claude Code |
| apple-remindersAtomicBot-ai/atomic-agent | Skill | 3.4k | 8d ago | MIT | A | 31 | Claude Code, Codex |
| obsidianAtomicBot-ai/atomic-agent | Skill | 3.4k | 8d ago | MIT | A | 20 | Claude Code, Codex |
| ffmpegAtomicBot-ai/atomic-agent | Skill | 3.4k | 8d ago | MIT | A | 47 | Claude Code, Codex |