Borrowing it
Nothing to install: this file belongs to codysumpter-cloud/buddy-universal-agent-profile. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/codysumpter-cloud/buddy-universal-agent-profile/main/.claude/skills/libresprite-buddy/SKILL.mdgit clone --depth 1 https://github.com/codysumpter-cloud/buddy-universal-agent-profileWrote 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/codysumpter-cloud/buddy-universal-agent-profile/libresprite-buddy)<a href="https://agentmods.dev/skills/codysumpter-cloud/buddy-universal-agent-profile/libresprite-buddy"><img src="https://agentmods.dev/badge/skills/codysumpter-cloud/buddy-universal-agent-profile/libresprite-buddy.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 | $0.00149 | $0.02642 |
| Opus 5 | $0.00075 | $0.01321 |
| Sonnet 5 | $0.00030 | $0.00528 |
| Haiku 4.5 | $0.00015 | $0.00264 |
Grade A, and why
libresprite-buddy 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 7d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
libresprite-buddy
A hybrid sprite toolkit. Pillow is the pixel engine. LibreSprite is the editor / preview only. The entrypoint is a single dispatcher:
plugins/buap/skills/libresprite-buddy/scripts/buddy.py
Hard constraints (verified — build on these, do not relitigate)
- LibreSprite headless (
-b) scripting cannot do pixel ops. In batch mode theappobject only exposeslaunch, open, yield, createDialog, documentation— noactiveImage/activeSprite/pixelColor/command. The pixel API exists only in the GUI. So all automation here uses Python/Pillow, never LibreSprite CLI scripting. - LibreSprite CLI resize (
--scale,--shrink-to) is smooth/bilinear only (no nearest) → soft results. Do not use it for quality resizes; use theresizesubcommand. - Opening a file for preview works:
/Applications/LibreSprite.app/Contents/MacOS/libresprite <file>. Theopensubcommand shells to that — optional, GUI-only, best-effort. - Resize of the Buddy art is best-effort, not lossless. The source art is true
~116px anti-aliased color, not a clean low-res grid, so downscaling is a quality
reconstruction (
LANCZOS+ a lightUnsharpMask), not a pixel-perfect conversion.
Dependency
Requires Pillow. If it is missing the scripts exit with code 2 and print:
Install it with: pip3 install --user Pillow. Verified present on this machine as
Pillow 11.3.0 under python3 (3.9.6).
Subcommands
Run python3 .../buddy.py <subcommand> --help for full flags.
- resize
input output [--size 64] [--method lanczos-sharp|lanczos|nearest|box]Crisp-resize a PNG, or a whole directory of PNGs, preserving alpha. Defaultlanczos-sharp(LANCZOS + UnsharpMask) is tuned for the anti-aliased Buddy art; usenearestwhen the input is already clean low-res pixel art. - clone
source dest [--force]Copy a single template file, or a whole pose/rotation/animation directory, to a destination. - recolor
input outdir [--count N | --hue 0..1] [--size 64] [--method ...]Generate hue-shifted variants. Identity is preserved: fully transparent pixels stay transparent; near-gray/white pixels (face, eyes, outline) are kept; the warm belly-heart accent is kept; everything else rotates by the hue shift. Emits a native copy plus a resized copy per variant. - feature-swap
base feature output [--x N --y N] [--size 0] [--method ...]Alpha-paste a feature layer (alternate antennae / eyes / belly icon) onto a base buddy at an offset. Feature parts are user-supplied PNGs. - new-buddy
--outdir DIR [--name N] [--base FRAME] [--hue 0..1] [--feature PNG --fx --fy] [--size 64] [--procedural [--egg]]"New shape" generator. Two paths:- Pose reuse (preferred): pass
--base= a pose/rotation/animation frame from a Buddy pack (8 rotations, 24 animation sets), then apply recolor and/or feature-swap. Emits native + resized. - Procedural v1 (
--procedural): simple parametric primitives (round or--eggbody, dot eyes, smile, antennae, belly accent) drawn withPIL.ImageDraw.
- Pose reuse (preferred): pass
- open
file [--libresprite PATH]Preview a file in the LibreSprite GUI. Optional, GUI-only, best-effort.
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.
- 7d ago First seen · 159 lines · 149 tokens per session scan A 00a6c3f80cb9
libresprite-buddy is a skill published in the GitHub repository codysumpter-cloud/buddy-universal-agent-profile (2 stars, last pushed 21d ago), licensed Apache-2.0. It adds 149 tokens to every session and 2,642 once invoked, about $0.0007 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.