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 cerul-ai/cerul --skill cerulgit clone --depth 1 https://github.com/cerul-ai/cerulWrote 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/cerul-ai/cerul/cerul)<a href="https://agentmods.dev/skills/cerul-ai/cerul/cerul"><img src="https://agentmods.dev/badge/skills/cerul-ai/cerul/cerul.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.00243 |
| Opus 5 | $0.00015 | $0.00121 |
| Sonnet 5 | $0.00006 | $0.00049 |
| Haiku 4.5 | $0.00003 | $0.00024 |
Grade A, and why
cerul 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 8d 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
Cerul
Use the public cerul CLI when the answer depends on video or other indexed
long-form media. Do not guess what a speaker said.
Before a request, run cerul capabilities so unavailable capabilities are not
invented. For retrieval, use a user-authorized scope:
cerul search "query" --library-id library_...
For a grounded answer using the constrained Agent facade:
cerul ask "question" --library-id library_...
Never print, request in chat, or persist API keys or installation tokens. If
authentication is missing, tell the user to configure CERUL_API_KEY, or the
local CERUL_BASE_URL plus CERUL_INSTALLATION_TOKEN, outside the conversation.
Do not expand the requested library or asset scope. Do not change a
local-only execution policy. Present Evidence timestamps and Artifact links
from the response; do not fabricate citations.
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.
- 8d ago First seen · 32 lines · 30 tokens per session scan A f4e966e45ab6
cerul is a skill published in the GitHub repository cerul-ai/cerul (156 stars, last pushed 9d ago), licensed Apache-2.0. It adds 30 tokens to every session and 243 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
watch
Watch any video (URL, stream, or local path) via Watch Skill. Downloads, extracts scene-aware deduped frames, OCRs them, transcribes (captions first, then local Whisper — offline by default), indexes everything, and hands the result to the agent. Follow-up questions are answered from the persistent index without…
the-loop
The user built or changed something visual — a UI, an animation, a game, a generated video — and wants it verified, or asks "why does my UI look wrong", "check that the fix actually worked", "does the animation glitch". Use this to record the running thing, critique the recording against plain-language pass criteria…
asking-with-evidence
The user asks a question about a video that was already watched or indexed — "what did they say about X", "what error code appears", "what happens at 2:30", "does the video show Y". Use this to answer from the persistent index with timestamped evidence and a confidence score instead of re-watching or guessing.
configuring-vision
The user wants to connect an LLM or vision provider, already has an API key, asks "can I use OpenAI/Anthropic/Gemini/OpenRouter", wants local Ollama, or needs different cheap and strong models. Use this to configure provider-neutral visual understanding without tying Watch Skill to one agent or model vendor.
extracting-structure
The user wants structure pulled out of a watched video — "make chapters for this video", "where does the bug appear in this recording", "turn this screen recording into a bug report", "how strong is my intro/hook". Use this for deterministic extraction from the index — chapters with timestamps, a fileable bug report…
video-memory
The user asks about videos watched in the past or across sessions — "have we watched anything about X", "which video showed that error", "what did that meeting decide", "search my videos", or a question that spans several videos. Use this to search and answer from the persistent cross-video index instead of saying you…