Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add melodic-software/claude-code-plugins/plugin install pixel-artWrote 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/melodic-software/claude-code-plugins/sprite)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/sprite"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/sprite/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/melodic-software/claude-code-plugins/sprite"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/sprite.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 | $0.00135 | $0.01286 |
| Opus 5.5 | $0.00054 | $0.00514 |
| Sonnet 5.5 | $0.00027 | $0.00257 |
| Haiku 4.5 | $0.00014 | $0.00129 |
Grade A, and why
sprite 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 17d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sprite
Produce a static sprite the user can drop into a game or project, and show it to them.
1. Brief
Follow brief.md. That file is the only copy of the
fields: subject, style references, proportions, size, palette, view, mood, target, and 2 to 6 done
criteria. Ask only what changes the output. State every unspecified field as a default in one line.
Write brief.md beside the spec before the first render. A later run that finds it there reads it
and does not ask again.
When the request is vague or high-stakes, offer /planning:interview (if the planning plugin is
installed). Planning owns a numbered-question brief. If planning is not installed, or the user does
not accept, continue with the in-skill brief, which is the default and works alone. Do not start
the interview unless the user accepts.
2. Choose the backend
Read backends.md. native is the default and
always available. Honor ${user_config.backend} when it names another backend and that backend
is present; when it is absent, say so and fall back to native. Every backend honors the same
artifact contract: the spec and the files in step 4.
3. Author
Write the spec that render.py reads (its docstring is the format). Two authoring modes:
- Hand-authored grid: small sprites (up to about 24x24), icons, faces. Write rows directly.
- Procedural generator: larger sprites or families of variants. Write a short Python script that draws with primitives (rects, ellipses, lines) onto a material grid, then applies shading and outlining passes and emits the spec JSON. Materials map to color ramps (highlight, base, shadow, line), which keeps the palette locked and makes recolors one-line edits.
The spec palette may be an inline object, a bundled preset name, or a path to a project palette
file (palettes/README.md). When the project has
pixel-art-palette.json (or another path its CLAUDE.md names), use that path instead of
inventing colors. Do not retype a preset by hand. Images from another backend are snapped with
render.py --snap (see backends.md), not by eye.
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.
- 17d ago Changed · +9 lines db9db7501196
- 18d ago First seen · 86 lines · 135 tokens per session scan A e80c2fbec384
sprite is a skill published in the GitHub repository melodic-software/claude-code-plugins (25 stars, last pushed today), licensed MIT. It adds 135 tokens to every session and 1,286 once invoked, about $0.0005 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 2026-09-28.
Other skills, from other repositories
find-shortest-path
For pathfinding and search: shortest path, maze solving, game AI, route planning, graph traversal, BFS/DFS, Dijkstra, A problems.
stack-based-backtrack
For search with undo: explicit decision stack, backtracking when paths fail, depth-first exploration with state restoration.
solve-grid-maze
For 2D grid problems: mazes, board games, tile maps, pixel grids, coordinate systems, cellular automata, flood fill. Uses dict-based Grid class pattern.
use-sparse-set
For sparse data: infinite grids, large spaces with few active elements, membership testing, set operations on coordinates or states.
parallel-worker
Execute focused implementation tasks in a parallel workflow. Use when: working on assigned files in a worktree, making checkpoint commits, signaling dependencies or blockers, completing orchestrator-assigned tasks. Triggers: worker, checkpoint, worktree, assigned scope, commit prefix, parallel task.
generate-tree-structure
For tree/maze generation: spanning trees, random mazes, graph coverage. Uses frontier-based exploration with configurable traversal order.