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 cyyprezz/krita-codex-mcp --skill krita-controlgit clone --depth 1 https://github.com/cyyprezz/krita-codex-mcpWrote 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/cyyprezz/krita-codex-mcp/krita-control)<a href="https://agentmods.dev/skills/cyyprezz/krita-codex-mcp/krita-control"><img src="https://agentmods.dev/badge/skills/cyyprezz/krita-codex-mcp/krita-control/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/cyyprezz/krita-codex-mcp/krita-control"><img src="https://agentmods.dev/badge/skills/cyyprezz/krita-codex-mcp/krita-control.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 | $0.00072 | $0.00709 |
| Opus 5 | $0.00036 | $0.00354 |
| Sonnet 5 | $0.00014 | $0.00142 |
| Haiku 4.5 | $0.00007 | $0.00071 |
Grade A, and why
krita-control 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 8d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Krita Control
Use the bundled krita MCP server. Keep the workflow local-first and preserve the user's active
document, filesystem boundaries, and undo history.
Start with a verified session
- Call
krita_statebefore any edit. - Read the returned connection, document, layer, and compatibility information. Stop if the bridge is unavailable or the requested feature is incompatible.
- Call
krita_previewbefore changing visible content. Use a cropped preview when the task targets a small region. - Reuse the returned
document_idandlayer_idvalues. Do not guess identifiers from names.
If the bridge is unavailable, explain that the user must install and enable Krita Codex Bridge,
restart Krita, and run krita-codex-install check. Do not install software, change allowed roots,
or edit user-wide Codex configuration without explicit permission.
Choose the narrowest tool
- Use
krita_stateandkrita_previewfor inspection. - Use
krita_documentfor compatibility, document lifecycle, and KRA saves. - Use
krita_canvasfor canvas geometry, color sampling, and raster-layer imports. - Use
krita_layersfor layer creation, activation, properties, ordering, and transforms. - Use
krita_brush,krita_paint_path, andkrita_drawfor native Krita marks and shapes. - Use
krita_editfor selections, clipboard operations, fills, and clears. - Use
krita_colorfor project colors, palettes, replacement, and filters. - Use
krita_historyfor bounded undo and redo. - Use
krita_save_exportfor KRA and PNG output. - Use
krita_assetfor layer, animation, tileset, and named-region packages.
Apply edits safely
- Serialize mutating tool calls. Do not edit the same document concurrently.
- State the exact document, layer, region, and output path before a destructive operation.
- Keep
overwrite=falseunless the user explicitly authorizes replacing the exact target. - Keep every input and output path beneath the configured allowed roots. Never widen those roots as a convenience.
- Call
krita_previewafter each meaningful visual change. Callkrita_stateafter layer-tree or document-lifecycle changes. - Save a KRA checkpoint before a long or hard-to-reverse sequence when the user has provided an allowed destination.
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.
- 8d ago First seen · 57 lines · 72 tokens per session scan A b4aa5ea3ccae
krita-control is a skill published in the GitHub repository cyyprezz/krita-codex-mcp (4 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 709 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
xiaobei-skill-academic-paper-to-ppt
A workflow that turns academic papers, reports, and technical documents into presentation slides, optionally following a supplied PowerPoint template. It creates a written outline, full-slide images, and a PowerPoint file.
reader-persona
Builds 3-5 reader personas representing the book's target audience segments. Each persona has reading habits, emotional triggers, deal-breakers, discovery channels, and comp title preferences. Used by writer (voice calibration), evaluator (4-reader simulation), and packager (marketing targeting).
maya-render
Pipeline stage — render globals, final-frame rendering, and viewport capture: configure render settings, query them, render frames, capture playblasts. Use for producing final or preview imagery. Not for modeling (maya-mesh-ops), animation editing (maya-animation), generic file import/export (maya-geometry), or render…
maya-scripting
Bootstrap stage — escape hatch for Maya work that has no packaged skill yet. Agents should prefer searchskills / dcccapabilitymanifest → loadskill → typed tools (inputSchema + annotations) from domain skills; use executepython or executemel only when no skill matches, for bulk in-process loops, or for API…
dcc-mcp-maya-setup
Set up dcc-mcp-maya for an agent or operator: install Maya Python dependencies with mayapy, generate MCP host configuration, guide the user through loading the Maya plugin, and run a first live-tool smoke prompt.
gigachat-image
An image-generation workflow for GigaChat, an AI service that creates pictures from text descriptions. It also supports checking the remaining usage allowance and adding an uploaded reference image.