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 agentmods add skills/krzysztofsurdy/code-virtuoso/image-annotatenpx 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.svg" alt="Measured on agentmods" 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 | $0.00117 | $0.03129 |
| Opus 5 | $0.00059 | $0.01564 |
| Sonnet 5 | $0.00023 | $0.00626 |
| Haiku 4.5 | $0.00012 | $0.00313 |
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 2d 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 — 268 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. Single CLI, one-off flags for simple marks, JSON spec file for compositions. Output is a flat raster image with every mark burned in - the original is never modified in place.
Core Principles
| Principle | Meaning |
|---|---|
| Never modify in place | Always write to a new output file. Annotation is destructive - the user must keep the original to redo or refine later. |
| Blur is not redaction | Pixelation and blur can be reversed for text content. 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 should read on any background | Use stroke + 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 coloured stroke over the underlying pixels, never relies on transparency alone. |
| Coordinate origin is top-left | All (x, y) coordinates start from the top-left corner of the image. Y increases downward. Match the convention to whatever the source tool reports - browser DevTools and most screenshot tools agree on this. |
| One operation, one purpose | A single annotation does one thing. To layer marks, repeat flags or use a JSON spec - do not try to overload one operation. |
| Burn into a flat image | The output is a single-layer PNG or JPEG. No editable layers, no SVG re-edit path. If the user needs to iterate, they re-run the script with a new spec. |
Quick Start
Install (one-time, ask user first)
pip install --user Pillow
Pillow is the imaging library. Cross-platform, pure-Python install. Check first:
python -c "import PIL; print(PIL.__version__)"
Simple one-off: rectangle + arrow + label
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.
- 2d 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 (20 stars, last pushed 3mo ago), licensed MIT. It adds 117 tokens to every session and 3,129 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 2026-09-03.
Other skills, from other repositories
hermes-diagnostic-review
Use when running a read-only diagnostic review of recent Hermes sessions to find recurring mistakes, failed tool calls, and repeated fixes, then propose suggestion-only improvements and reusable skills. Human-gated; never auto-applies.
instruction-eval
Change one condition an agent runs under (instruction text, the reference material instructions point at, MCP tools and permissions, hooks, skill files), then run the same prompts before and after, several times each, to see what actually changes. Produces an HTML report showing both arms' answers side by side. Use…
worth-building
Decide how elaborate to build something (simple vs. robust) and return a concrete, PoC-shaped proposal at that level — not over- or under-engineered, but right-sized. Use whenever someone is building something and the investment level is unclear: "quick or proper?", "MVP vs. real product", "is this over-engineering?"…
django-ticket-triage
Analyze a Django Trac ticket and produce a triage recommendation report — duplicate search, related PRs, forum threads, and the affected source code. Use when the user gives a Django ticket number, or asks whether a ticket is valid, a duplicate, or ready for a triage stage.
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…
healthcheck
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).