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 SinanTufekci/agent-intern --skill imagegit clone --depth 1 https://github.com/SinanTufekci/agent-internWrote 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/sinantufekci/agent-intern/image)<a href="https://agentmods.dev/skills/sinantufekci/agent-intern/image"><img src="https://agentmods.dev/badge/skills/sinantufekci/agent-intern/image/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/sinantufekci/agent-intern/image"><img src="https://agentmods.dev/badge/skills/sinantufekci/agent-intern/image.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 | $0.00054 | $0.00416 |
| Opus 5.5 | $0.00022 | $0.00166 |
| Sonnet 5.5 | $0.00011 | $0.00083 |
| Haiku 4.5 | $0.00005 | $0.00042 |
Grade A, and why
image 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 1mo 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
Generate an image for: $ARGUMENTS
- Pick the output path. If the request names one, use it. Otherwise choose a descriptive kebab-case
file name. Put it in an existing
assets/,images/,public/ordocs/directory if the project has one, else in the project root. Pass it as an absolute path. - Write a concrete prompt. Cover the subject, style, composition, colour palette, background and aspect ratio. Keep any text the image must show short and quote it exactly, because image models misspell long text.
- Call
antigravity_imagewith that prompt, theoutput_path, andworkspaceset to the project root. For several variations, callantigravity_image_swarminstead, with one prompt per variation. - Use the path the tool returns. Gemini picks PNG or JPEG itself, and the tool renames the file to
match the real bytes, so
hero.pngmay come back ashero.jpg. - Look at the result. Read the saved image and check it matches the request. If it clearly misses, for example the wrong subject or garbled text, say what's wrong and offer one retry with an adjusted prompt. Don't retry silently in a loop.
This needs the Antigravity backend: agy, signed in to Google AI Pro. If antigravity_image reports
that agy is missing or not signed in, tell the user and suggest /agent-intern:doctor.
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.
- 1mo ago First seen · 26 lines · 54 tokens per session scan A 4bcfc5c04f97
image is a skill published in the GitHub repository SinanTufekci/agent-intern (32 stars, last pushed 3d ago), licensed MIT. It adds 54 tokens to every session and 416 once invoked, about $0.0002 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 2026-09-25.
image compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| imageSinanTufekci/agent-intern | Skill | 32 | 3d ago | MIT | A | 54 | Claude Code |
| agent-framework-azure-ai-pysickn33/agentic-awesome-skills | Skill | 50k | today | MIT | A | 24 | Claude Code |
| conductor-implementgemini-cli-extensions/conductor | Skill | 3.8k | 2mo ago | Apache-2.0 | A | 34 | Claude Code, Codex |
| quantum-vqlsxi-zhao/OpenQuantum | Skill | 72 | yesterday | MIT | A | 56 | Claude Code, Codex |
| octave-compressionelevanaltd/octave-mcp | Skill | 52 | 6d ago | Apache-2.0 | A | 36 | Claude Code |
| django-expertpersonamanagmentlayer/pcl | Skill | 45 | 21d ago | Apache-2.0 | A | 47 | Claude Code |
| craque-netomarioluciofjr/skills | Skill | 18 | 14d ago | Apache-2.0 | A | 249 | Claude Code, Codex |