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 hertz-ai/HARTOS --skill reel_editgit clone --depth 1 https://github.com/hertz-ai/HARTOSWrote 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/hertz-ai/hartos/reel_edit)<a href="https://agentmods.dev/skills/hertz-ai/hartos/reel_edit"><img src="https://agentmods.dev/badge/skills/hertz-ai/hartos/reel_edit/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/hertz-ai/hartos/reel_edit"><img src="https://agentmods.dev/badge/skills/hertz-ai/hartos/reel_edit.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 | $0.00018 | $0.00511 |
| Opus 5.5 | $0.00007 | $0.00204 |
| Sonnet 5.5 | $0.00004 | $0.00102 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
reel_edit 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.
What it actually says
reel_edit
reel_make plans every cut. You make a few choices and tell her plainly what it cannot do.
What reel_make does
- Clips play in the order she filmed them, so the look builds stage by stage: bare face, base, eyes, lips, hair, jewellery. Weak or repeated shots are dropped; none moves out of time.
- If she filmed the finished look, it ends on its best shot, held about 2-4 s and never under 1.5 s. Without one there is no reveal: never promise one.
- Every cut lands on a beat: her song's when she attaches its audio, else a steady 120 BPM. The file is silent; she adds the song in Instagram at the start time given.
- Pace is set by what she said when she made this agent: about 1.5 s a shot, or 2.5 s if she asked for a calm pace. You cannot change it for one reel; tell her so if she asks.
- Hard cuts only, no fades or wipes. The only words on screen are your hook_text; her caption goes in the post.
- The face sits high in the frame. Your line and her logo stay clear of Instagram's buttons.
What you choose
- target_seconds: 5-30 s, 20 s by default.
- The first second decides if anyone stays. The reel opens on her earliest shot, usually the bare face, under hook_text for 2 s: at most 6 words that promise the change. Draft it with ig_reel.
- open_with=final_look only when she asks to start with the result (a teaser of 1 s at most).
- song_key: from reel_trending_songs.
Bridal footage
- One clip per stage, hair, maang tikka and nath included. Phone upright, window daylight: bulb light yellows skin, and a dark first frame gets the reel withheld.
- Hold the finished look at least 4 s, the bride turning slowly, so the reveal never needs slowing.
- Name the occasion in her words: muhurtham, haldi, mehendi, sangeet, reception.
- Show a bride's face only with the bride's consent.
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 · 31 lines · 18 tokens per session scan A ce5bb34acd57
reel_edit is a skill published in the GitHub repository hertz-ai/HARTOS (51 stars, last pushed today), licensed Apache-2.0. It adds 18 tokens to every session and 511 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 2026-10-18.
Other skills, from other repositories
tmux
Use when a CLI task needs an interactive terminal or control of a tmux session.
github
Manage GitHub issues and pull requests, inspect CI runs, and query repository data.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.
python-development
Coding standards, conventions, and patterns for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files in the python/ directory.