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 ig_humangit 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/ig_human)<a href="https://agentmods.dev/skills/hertz-ai/hartos/ig_human"><img src="https://agentmods.dev/badge/skills/hertz-ai/hartos/ig_human/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/ig_human"><img src="https://agentmods.dev/badge/skills/hertz-ai/hartos/ig_human.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 | $0.00033 | $0.00394 |
| Opus 5.5 | $0.00013 | $0.00158 |
| Sonnet 5.5 | $0.00007 | $0.00079 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
ig_human 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
ig_human
Captions are short and scripts are said out loud, so one written-sounding line stands out.
What reel_check_caption fixes by itself
- Invisible characters, em dashes, curly quotes. Joiners inside Tamil or Hindi letters and inside emoji are kept.
- Stock words: "elevate", "game-changer", "in today's fast-paced world", "follow for more". Words in her profile are kept.
What you fix by hand
It reports sentence shapes it will not rewrite:
- "It's not just X, it's Y" and "not only X but also Y"
- lists of exactly three
- "The result?" lines
- emoji bullet lists
- three or more words in capitals
- "tag someone who", "double tap if" Rewrite each one, keep the meaning, then check again. Two rounds is normal; five means write a new draft.
The score
Five checks, 0-100, higher is more human: BURSTINESS (sentence lengths vary), SPECIFICITY (numbers, names, places, occasions), SLOP DENSITY (stock words), FINGERPRINT (typography), VOICE (I and you, no staged reveals). PASS needs 70 or more with no check under 55. Fix the weakest check first.
Say it honestly
These are local checks on her computer. They are not GPTZero or any other detector and cannot promise their verdict. Never tell her a text is undetectable. Show her the cleaned text, not only the score.
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 · 33 tokens per session scan A 33705e201e86
ig_human is a skill published in the GitHub repository hertz-ai/HARTOS (51 stars, last pushed today), licensed Apache-2.0. It adds 33 tokens to every session and 394 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.