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 kitao/pyxel-skill --skill pyxel-skillgit clone --depth 1 https://github.com/kitao/pyxel-skillWrote 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/kitao/pyxel-skill/pyxel-skill)<a href="https://agentmods.dev/skills/kitao/pyxel-skill/pyxel-skill"><img src="https://agentmods.dev/badge/skills/kitao/pyxel-skill/pyxel-skill/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/kitao/pyxel-skill/pyxel-skill"><img src="https://agentmods.dev/badge/skills/kitao/pyxel-skill/pyxel-skill.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 | $0.00063 | $0.00894 |
| Opus 5.5 | $0.00025 | $0.00358 |
| Sonnet 5.5 | $0.00013 | $0.00179 |
| Haiku 4.5 | $0.00006 | $0.00089 |
Grade A, and why
pyxel 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 6d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pyxel
Build or change only what the request needs, preserving the existing game's conventions. Verify the result from observed behavior, with effort proportional to the task.
Runtime
pyxel-mcp provides eight observation tools. They report facts; judging them is your job.
validatereports syntax errors and recognizable Pyxel code patterns without running the script.rundrives headless frames with scheduled input, stops onuntil, and capturesstate,screen_image,screen_grid, orvideo.screen_imagewithinline: truereturns an image.pyxel_inforeports versions, bundled examples, and resource URIs.read_palette,read_image,read_tilemap, andread_audioinspect the palette, image banks, tilemaps, and rendered audio;read_imageandread_tilemaptakeinline=trueto return their renders as images.diff_framescompares two captured PNGs.
If tools are missing or pyxel_info reports a version below 1.3.1, update the plugin or set the client's MCP command to uvx --from 'pyxel-mcp>=1.3.1' pyxel-mcp. Append install for setup examples; it only prints instructions. Apply the appropriate registration with this versioned command. Avoid duplicate plugin registrations. Restart the client and recheck pyxel_info. While blocked, use focused logic tests plus direct headless Pyxel runs, and report weaker visual and interaction verification.
Workflow
- Identify the requested behavior and the existing code and assets it affects. For a new game, choose a playable scope with controls, an objective, and any retry or terminal states its rules need. Ask only when a missing choice materially changes the result.
- Implement the change. Follow the project's asset conventions; use code-generated or file-based assets as the task requires.
- Run
validateon changed game code. Fix errors and resolve or explain relevant warnings. Exercise the affected behavior withrun, using scheduled input and arandom_seedwhen randomness matters. Check that it reaches the intended stop without crash, timeout, or unexpected stall; readlogeven whenokis true. - Check task-specific state predicates for mechanics and directly inspect captured frames for appearance. A new game needs both; a focused edit needs evidence for the behavior it can affect. Use
screen_imagewithinline: trueto see the frame. Check authored audio throughread_audio, and listen before judging sound quality. Fix observed defects and repeat affected checks; use focused logic tests when they prove rules more directly. - Report changed files, controls when relevant, verification results, and anything unverified. Distinguish observed behavior from visual or listening judgments.
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.
- 6d ago Changed 25fb90586971
- 1mo ago Changed · -14 lines 59eea1fb126c
- 1mo ago Changed 09c4b43c9602
- 1mo ago Changed · +4 lines · +21 tokens per session 4fd80f72e468
- 2mo ago First seen · 56 lines · 42 tokens per session scan A 4563b35dfec4
pyxel is a skill published in the GitHub repository kitao/pyxel-skill (15 stars, last pushed 7d ago), licensed MIT. It adds 63 tokens to every session and 894 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
pygame-core
Structure a pygame (pygame-ce) game in Python: the init/event/update/draw loop, delta-time movement, Surface/Rect blitting, keyboard/mouse input, and Sprite/Group management with collision. Use when building or debugging a pygame game — when the user mentions pygame, pygame-ce, the game loop, blit, Surface, Rect…
vibeue
Unreal Engine 5 development using the VibeUE Python API. Use when working in Unreal Engine — blueprints, state trees, materials, actors, landscapes, animation, niagara, widgets, sound, foliage, gameplay tags, enhanced input, skeletons, PCG (procedural content generation), and more. VibeUE is an extension of Unreal's…
demo-1-terminal-arcade
Demo skill that builds a colorful, playable terminal Snake game in a single pure-stdlib Python curses file — score HUD, speed ramp, eat/death animations, and a game-over screen.
python-lsp
Semantic Python code queries via a stdio LSP client driving pyright-langserver. Provides binding-resolved go-to-definition, find-references, hover types, type diagnostics, file symbol outlines, and project-wide symbol search — name resolution and type inference that tree-sitter and ripgrep cannot do. Use when you need…
searching-codebases
Binding-resolved Python symbol queries via pyright — every true caller (--refs), the real definition (--def), or an inferred signature (--hover) of a .py symbol, excluding the same-named false positives text search cannot tell apart. Use when a task needs ALL callers or users of a named Python symbol and grep would…
HA Integration Dev
Home Assistant custom integration development in Python. Covers customcomponents, DataUpdateCoordinator, configflow, OAuth2, conversation agent, HACS publishing, device registry, entity platforms, services, repair issues, diagnostics, Bluetooth integrations, and multi-coordinator patterns.