Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/cerul-ai/cerulnpx agentmods add skills/cerul-ai/cerul/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/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/cerul-ai/cerul/cerul"><img src="https://agentmods.dev/badge/skills/cerul-ai/cerul/cerul.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 | $0.00033 | $0.04055 |
| Opus 5.5 | $0.00013 | $0.01622 |
| Sonnet 5.5 | $0.00007 | $0.00811 |
| Haiku 4.5 | $0.00003 | $0.00405 |
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 9d 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 — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cerul
Cerul turns local video into searchable, annotated data using the user's own model endpoints. There is no account and no server to start: run the binary and read its output. Sidecar files beside each video are authoritative; search indexes are caches that rebuild from them without model calls.
Before anything else
Run cerul --version. If it is missing, follow the installation runbook at
https://github.com/cerul-ai/cerul/blob/main/docs/agent-setup.md. Do not install
Rust, Python, Ollama, or system FFmpeg for this workflow, and do not switch to a
source build when a download fails; report the error instead.
cerul --json upgrade reports the newest published release and installs
nothing. It replaces the program only with --yes, so ask the user before
running cerul upgrade --yes: it changes which build answers every later
command. A build too old for a flag you need is a reason to offer the upgrade,
not to work around it.
Run cerul --json auth to see whether a key is available. It reports whether a
key is saved or exported, never the value. Never echo a key, print part of it,
write it to a log or a commit, or read an unrelated project's .env. When no key
is available, ask the user to run cerul auth set in their own terminal, or to
export the key themselves.
Always pass --json
--json is the machine contract, and it is the only mode to use:
- stdout carries exactly one JSON object, printed when the command finishes.
- stderr carries one JSON event per line while the command runs.
- Nothing ever prompts. A missing argument returns
invalid_arguments, not a question.
Exit codes: 0 success, 2 arguments or configuration, 3 unavailable
dependency or capability, 4 execution failure, 5 cancelled, 6 partial
success. Read the code as well as the output. Exit 6 is not success: part of
the work finished and the rest did not.
Events on stderr:
progresscounts units of work for one station.annotation_progressreports annotation work units, cached units and phase; percentage is completed planned work, not model-internal progress.checkpointmarks a window that is saved and will be reused after an interruption, so a rerun resumes rather than repeating it.publishedmarks a validated annotation file that now exists, with its record count and path. Only a published file is safe to read or train on.logcarries human-readable notices.
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.
- 9d ago Changed 28592f43de97
- 13d ago Changed · +53 lines · +6 tokens per session e0f4b1648777
- 23d ago Changed a6cbc96bd223
- 24d ago Changed · -62 lines · -48 tokens per session 36e0e04b69a3
- 1mo ago Changed a630bb1dfe5d
- 1mo ago Changed · +1 lines 22d8026cdbe9
- 1mo ago Changed 2d22daf82573
- 1mo ago Changed · +86 lines a60cd015daf7
- 1mo ago Changed · +20 lines 4865c19bd116
- 1mo ago First seen · 241 lines · 75 tokens per session scan A 5993f6eedc6c
cerul is a skill published in the GitHub repository cerul-ai/cerul (166 stars, last pushed 10d ago), licensed Apache-2.0. It adds 33 tokens to every session and 4,055 once invoked, about $0.0001 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
multimodal-stable-diffusion
State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.
vss-generate-video-report
Use this skill when producing a VSS analysis report — Mode A per-clip VLM, Mode B incident-range via video-analytics, Mode C SOP compliance via the SOP tools. Not for standalone video summarization, real-time alerts or ad-hoc Q&A.
rtvi-vlm-perf-testing
Plan, run, and diagnose reproducible RT-VLM GPU performance canaries and benchmarks. Use this skill when running fresh-container stream-capacity, semantic-isolation, latency, throughput, or regression experiments against an RTVI microservices checkout.
vss-generate-video-calibration
Use this skill when running or tuning AutoMagicCalib on local MP4s, RTSP, or the bundled sample dataset, or when deploying vss-auto-calibration. Do not use for non-AMC calibration or runtime analytics.
vss-manage-video-io-storage
Use to drive vss vios for sensor list, timelines, clips, snapshots, and add/delete of video or stream sources, and the VIOS REST API only for what that CLI does not cover (sensor info/status/settings, storage and recorder status, WebRTC, the RTSP proxy, network scan, device settings, bytes to disk, the NvStreamer…
vss-ask-video
Use this skill when answering a question about previously analyzed or freshly scoped VSS video, or when reading a stored VSS memory job or record by id, or whenever a question should be answered by running the vss memory introspect command. Route through hot context, agent Markdown notes, vss memory get or vss memory…