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 krzysztofsurdy/code-virtuoso --skill image-annotategit clone --depth 1 https://github.com/krzysztofsurdy/code-virtuosoWrote 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/krzysztofsurdy/code-virtuoso/image-annotate)<a href="https://agentmods.dev/skills/krzysztofsurdy/code-virtuoso/image-annotate"><img src="https://agentmods.dev/badge/skills/krzysztofsurdy/code-virtuoso/image-annotate/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/krzysztofsurdy/code-virtuoso/image-annotate"><img src="https://agentmods.dev/badge/skills/krzysztofsurdy/code-virtuoso/image-annotate.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 | $0.00052 | $0.03908 |
| Opus 5.5 | $0.00021 | $0.01563 |
| Sonnet 5.5 | $0.00010 | $0.00782 |
| Haiku 4.5 | $0.00005 | $0.00391 |
Grade A, and why
image-annotate 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 3d 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 — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Annotate
Mark up an existing image with shapes, text, numbered steps, blur, or solid-color redaction. It is a single CLI: one-off flags for simple marks, a JSON spec file for compositions. The output is a flat raster image with every mark burned in, and the original is never modified in place. The output filename always reflects what was done. Pass --name PURPOSE to label the artifact by intent, or omit the output path and let the script derive a descriptive name from the operations applied.
Core Principles
| Principle | Meaning |
|---|---|
| Never modify in place | Always write to a new output file. Annotation is destructive, so the user must keep the original to redo or refine later. |
| Output names describe intent | Either pass --name some-purpose to label the artifact, or omit the output argument and the script derives a name from the ops applied (e.g. screenshot-rect-arrow-text.png). Collisions get a -2, -3 suffix, so a repeated run never overwrites an earlier result. |
| Blur is not redaction | Pixelation and blur can be reversed for text. For passwords, API keys, SSNs, payment numbers, and other security-critical strings, use solid-color redaction. Blur is acceptable only for casual privacy (faces in marketing shots, peripheral background detail). See references/redaction-safety.md. |
| Marks must read on any background | Use stroke and fill colors that contrast with the surrounding pixels, or add a contrasting outline to text. Yellow on a yellow page is invisible. The default style stacks a thick colored stroke over the underlying pixels and does not rely on transparency alone. |
| Coordinate origin is top-left | All (x, y) coordinates start from the top-left corner of the image. Y increases downward. Browser DevTools and most screenshot tools use the same convention. |
| One operation, one purpose | A single annotation does one thing. To layer marks, repeat flags or use a JSON spec. Do not overload one operation. |
| Burn into a flat image | The output is a single-layer PNG or JPEG. There are no editable layers and no SVG path for re-editing. To iterate, re-run the script with a new spec. |
What ships with it
3 files 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.
- 3d ago Changed · +24 lines 14fad4b171dc
- 4d ago Changed · +10 lines · -65 tokens per session acd8caab8b22
- 1mo ago First seen · 268 lines · 117 tokens per session scan A 0988cddf6753
image-annotate is a skill published in the GitHub repository krzysztofsurdy/code-virtuoso (36 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 3,908 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 2026-09-03.
Other skills, from other repositories
html-visual
Generate an interactive single-file HTML visualization — mockup, wireframe, ERD, flowchart, chart, slides, architecture diagram, dashboard, timeline, mindmap, kanban, or table. Use when the user wants something rendered rather than described: a UI mockup or wireframe, a database schema as an ERD, business logic as a…
sag
ElevenLabs text-to-speech with mac-style say UX.
claude-design
Use this skill when the user asks for design work that would normally fit Claude Design, but the agent is running in a CLI/API environment instead of the hosted Claude Design web UI.
marketing-collateral-design
Use this skill to create professional static promotional graphics whose typography, claims, and contact details must remain exact. The core production rule is hybrid, not one-shot: generate or source imagery separately, then compose real text and vector elements deterministically in HTML/CSS/SVG. Image models are art…
hermes-themes
Author a Hermes skin — one YAML file that themes the CLI, the TUI, and the desktop GUI at once. The skin engine (hermescli/skinengine.py) resolves the active skin and the gateway pushes it to every surface, so a file dropped in /.hermes/skins/ is the theme analogue of a plugin: no code, all surfaces. This skill covers…
design-an-interface
Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".