Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/understudy-ai/understudy/taught-create-a-background-removed-portrait-for-a-requested-person-and-send-it-i)<a href="https://agentmods.dev/skills/understudy-ai/understudy/taught-create-a-background-removed-portrait-for-a-requested-person-and-send-it-i"><img src="https://agentmods.dev/badge/skills/understudy-ai/understudy/taught-create-a-background-removed-portrait-for-a-requested-person-and-send-it-i/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/understudy-ai/understudy/taught-create-a-background-removed-portrait-for-a-requested-person-and-send-it-i"><img src="https://agentmods.dev/badge/skills/understudy-ai/understudy/taught-create-a-background-removed-portrait-for-a-requested-person-and-send-it-i.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 | $0.00113 | $0.02532 |
| Opus 5 | $0.00056 | $0.01266 |
| Sonnet 5 | $0.00023 | $0.00506 |
| Haiku 4.5 | $0.00011 | $0.00253 |
Grade A, and why
taught-create-a-background-removed-portrait-for-a-requested-person-and-send-it-in-telegram-cd861a 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 12d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
taught-create-a-background-removed-portrait-for-a-requested-person-and-send-it-in-telegram-cd861a
This workspace skill was taught from an explicit teach draft captured in /Users/songliang/workspace/Understudy/understudy.
Overall Goal
Produce and send a clean transparent cutout image for a requested person via Telegram.
Staged Workflow
- Obtain a suitable portrait image for the requested person, using a provided local file or direct image URL when available, otherwise finding a clear single-subject portrait from an acceptable source. Notes: Prefer a source image with minimal occlusion and enough separation from the background for reliable cutout.
- Open the chosen image in an editor that can remove backgrounds and produce a transparent PNG. Notes: The demo used Pixelmator Pro for the background-removal step.
- Remove the background and verify that the subject is isolated cleanly on transparency before delivery. Notes: Do not send obvious cutout failures; visually confirm the result first.
- Open the target Telegram chat, attach the processed transparent image, and send it with no caption by default. Notes: Captionless delivery is the confirmed default behavior.
GUI Reference Path
The GUI reference path below is for replay and grounding reference only.
- Open a suitable portrait result from the image grid. target: image result tile showing the requested person in the Google Images results grid | app: Google Chrome | scope: Google Images results page
- Open the source image in Pixelmator Pro or another installed editor with visible background-removal capability. reference: [preferred] [gui/gui_click] | when: When performing the native desktop editing flow shown in the demo. | notes: The demonstrated editing path was desktop-native rather than browser-native. | target: menu item "Remove Background" in the image editor | app: Pixelmator Pro | scope: editor menu or command surface
- Run the editor's background-removal action and verify that a transparent result is shown. reference: [preferred] [gui/gui_click] | when: When using Pixelmator Pro or a similar native editor UI. | notes: This is the core transformation step demonstrated in the recording. | target: menu item "Remove Background" in the image editor | app: Pixelmator Pro | scope: editor menu or command surface
- Open Telegram, choose the target chat, attach the processed transparent image, and send it without a caption by default. reference: [preferred] [gui/gui_click] | when: When using Telegram desktop for delivery. | notes: Observed delivery route in the demo, with confirmed default caption behavior. | target: paperclip icon button next to the message input in Telegram | app: Telegram | scope: chat composer
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.
- 12d ago First seen · 169 lines · 113 tokens per session scan A c2fbe9f97841
taught-create-a-background-removed-portrait-for-a-requested-person-and-send-it-in-telegram-cd861a is a skill published in the GitHub repository understudy-ai/understudy (456 stars, last pushed 2mo ago), licensed MIT. It adds 113 tokens to every session and 2,532 once invoked, about $0.0006 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
sherpa-onnx-tts
Local text-to-speech via sherpa-onnx (offline, no cloud).
gifgrep
Search GIF providers with CLI/TUI, download results, and extract stills/sheets.
meme-maker
Search meme templates, suggest formats, and generate local or hosted image memes.
openai-whisper-api
OpenAI Audio Transcriptions API via curl; gpt-4o-transcribe, mini, diarize, or whisper-1.
sag
ElevenLabs text-to-speech with mac-style say UX.
sonoscli
Control Sonos speakers (discover/status/play/volume/group).