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 tushaarmehtaa/tushar-skills --skill image-editinggit clone --depth 1 https://github.com/tushaarmehtaa/tushar-skillsWrote 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/tushaarmehtaa/tushar-skills/image-editing)<a href="https://agentmods.dev/skills/tushaarmehtaa/tushar-skills/image-editing"><img src="https://agentmods.dev/badge/skills/tushaarmehtaa/tushar-skills/image-editing/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/tushaarmehtaa/tushar-skills/image-editing"><img src="https://agentmods.dev/badge/skills/tushaarmehtaa/tushar-skills/image-editing.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 | $0.00035 | $0.00633 |
| Opus 5.5 | $0.00014 | $0.00253 |
| Sonnet 5.5 | $0.00007 | $0.00127 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
image-editing 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.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image editing
Requires an image-editing tool or configured API, image inspection, and access to the supplied references. Installing this skill does not provide model access.
Deliver edited images and a short report of requested changes, preserved details, and remaining defects. Follow the user's requested model, style, references, and output format.
Establish the edit
Inspect the supplied images and prior approved output before choosing a base. Distinguish the image to edit from references that establish identity, style, or layout. If a required reference is missing, request that file; do not invent its content. Infer routine details from the supplied brief rather than requiring a questionnaire.
For successive revisions, use the latest approved output as the edit base and keep the original identity reference available. Do not promote a failed draft to the new base. Read the edit record when tracking multiple references, revisions, or exact-copy requirements.
Write a compact change/preserve contract: the requested difference, details that must remain, exact text, and output dimensions. Resolve direct conflicts (such as changing a label while preserving all label text) before dependent work; continue independent inspection.
Select and use the tool
Inspect the available image tool's contract. Use its supported reference-image mechanism and editing operation. A text prompt describing a reference is not a substitute for attaching it. If using an API, verify the requested model ID, edit endpoint, supported parameters, and account access in current official documentation. Never claim that a tool selected a model when it does not expose model selection.
Use existing configured access. Do not place credentials in prompts, source files, or output logs. If editing is unavailable, return the prepared edit contract and name the missing capability; do not claim to have produced an image. A skill does not grant tool permissions or pay for model access.
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.
- 1mo ago First seen · 38 lines · 35 tokens per session scan A 152560032fb4
image-editing is a skill published in the GitHub repository tushaarmehtaa/tushar-skills (12 stars, last pushed 5d ago), licensed MIT. It adds 35 tokens to every session and 633 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 2026-09-10.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.