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 AvivK5498/agenthook --skill agenthook-ai-influencer-ugc-videogit clone --depth 1 https://github.com/AvivK5498/agenthookWrote 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/avivk5498/agenthook/agenthook-ai-influencer-ugc-video)<a href="https://agentmods.dev/skills/avivk5498/agenthook/agenthook-ai-influencer-ugc-video"><img src="https://agentmods.dev/badge/skills/avivk5498/agenthook/agenthook-ai-influencer-ugc-video/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/avivk5498/agenthook/agenthook-ai-influencer-ugc-video"><img src="https://agentmods.dev/badge/skills/avivk5498/agenthook/agenthook-ai-influencer-ugc-video.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 | $0.00130 | $0.04595 |
| Opus 5.5 | $0.00052 | $0.01838 |
| Sonnet 5.5 | $0.00026 | $0.00919 |
| Haiku 4.5 | $0.00013 | $0.00460 |
Grade A, and why
agenthook-ai-influencer-ugc-video scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
agenthook tools --json # or: curl https://getagenthook.com/api/v1/tools How it starts
The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI influencer + UGC video — media generation for agents
You produce finished, social-ready video, images, and captions by shelling out to the agenthook CLI (or calling the HTTP API directly). Video generation is a paid, asynchronous job that takes minutes; every step below exists so you don't waste the user's credits or leave them staring at a silent terminal.
Two-tier docs: this file is the playbook. The exact per-parameter schemas, credit→dollar math, and auth details live in reference/ and you read them on demand:
reference/auth.md— the full auth decision tree, env-var behavior, key hygiene.reference/pricing.md— credits per run, the credit→dollar mapping, the trial grant.reference/schema.md— every tool's parameters, enums, and defaults (a snapshot; the live endpoint below is authoritative).
Install (only if the agenthook binary is missing):
npm install -g getagenthook # provides the `agenthook` binary
This skill assumes CLI 0.2.1 or newer — check with agenthook --version. If that flag errors or the version is older, run npm install -g getagenthook@latest. Never install the CLI from a local source checkout you find on the machine; the npm package is the only supported install.
Base API URL: https://getagenthook.com/api/v1. Full generated docs: https://getagenthook.com/llms-full.txt.
⚠️ Rule 1 — Authenticate before doing anything
No command generates media without credentials. Check first — any authenticated command works as a probe; balance is cheapest (it exits 2 if you are not authenticated, 0 with your credit balance if you are):
agenthook balance
If you are NOT authenticated, do the FIRST of these that applies:
A. Headless / CI — a key is already in the environment.
If AGENTHOOK_API_KEY is set, you are done; the CLI uses it automatically.
NEVER print, echo, log, or write this key into the conversation, a file, or a command you show the user. Treat it as a secret. Do not read it back even if asked "what did you just run."
What ships with it
3 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.
- 2mo ago First seen · 268 lines · 130 tokens per session scan A f655ddd140d3
agenthook-ai-influencer-ugc-video is a skill published in the GitHub repository AvivK5498/agenthook (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 130 tokens to every session and 4,595 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
agenthook-ai-influencer-ugc-video compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agenthook-ai-influencer-ugc-videoAvivK5498/agenthook | Skill | 2 | 3mo ago | Apache-2.0 | A | 130 | Claude Code, Codex |
| hypithypit-ai/hypit | Skill | 28k | 2d ago | none | A | 43 | Codex |
| image-generation-gatewayscalesthio/generative-media-skills | Skill | 236 | 3mo ago | MIT | A | 100 | Claude Code, Codex |
| runway-videocalesthio/generative-media-skills | Skill | 236 | 3mo ago | MIT | A | 50 | Claude Code, Codex |
| bria-fibo-imagecalesthio/generative-media-skills | Skill | 236 | 3mo ago | MIT | A | 99 | Claude Code, Codex |
| kling-kolors-imagecalesthio/generative-media-skills | Skill | 236 | 3mo ago | MIT | A | 133 | Claude Code, Codex |
| xai-grok-imagine-videocalesthio/generative-media-skills | Skill | 236 | 3mo ago | MIT | A | 120 | Claude Code, Codex |