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 bighardperson/computer-science-skills-collection --skill glsl-shadergit clone --depth 1 https://github.com/bighardperson/computer-science-skills-collectionWrote 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/bighardperson/computer-science-skills-collection/glsl-shader)<a href="https://agentmods.dev/skills/bighardperson/computer-science-skills-collection/glsl-shader"><img src="https://agentmods.dev/badge/skills/bighardperson/computer-science-skills-collection/glsl-shader/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/bighardperson/computer-science-skills-collection/glsl-shader"><img src="https://agentmods.dev/badge/skills/bighardperson/computer-science-skills-collection/glsl-shader.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 | $0.00039 | $0.04415 |
| Opus 5.5 | $0.00016 | $0.01766 |
| Sonnet 5.5 | $0.00008 | $0.00883 |
| Haiku 4.5 | $0.00004 | $0.00441 |
Grade A, and why
shader-dev 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 1mo 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
60 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.
- _skillhub_meta.json 123 B
- reference/ambient-occlusion.md 14 KB
- reference/analytic-ray-tracing.md 24 KB
- reference/anti-aliasing.md 2.9 KB
- reference/atmospheric-scattering.md 28 KB
- reference/camera-effects.md 3.0 KB
- reference/cellular-automata.md 27 KB
- reference/color-palette.md 20 KB
- reference/csg-boolean-operations.md 18 KB
- reference/domain-repetition.md 18 KB
- reference/domain-warping.md 17 KB
- reference/fluid-simulation.md 19 KB
- reference/fractal-rendering.md 18 KB
- reference/lighting-model.md 29 KB
- reference/matrix-transform.md 18 KB
- reference/multipass-buffer.md 25 KB
- reference/normal-estimation.md 17 KB
- reference/particle-system.md 28 KB
- reference/path-tracing-gi.md 28 KB
- reference/polar-uv-manipulation.md 23 KB
- reference/post-processing.md 24 KB
- reference/procedural-2d-pattern.md 16 KB
- reference/procedural-noise.md 22 KB
- reference/ray-marching.md 15 KB
- reference/sdf-2d.md 28 KB
- reference/sdf-3d.md 27 KB
- reference/sdf-tricks.md 2.6 KB
- reference/shadow-techniques.md 21 KB
- reference/simulation-physics.md 28 KB
- reference/sound-synthesis.md 24 KB
- reference/terrain-rendering.md 32 KB
- reference/texture-mapping-advanced.md 3.3 KB
- reference/texture-sampling.md 26 KB
- reference/volumetric-rendering.md 28 KB
- reference/voronoi-cellular-noise.md 18 KB
- reference/voxel-rendering.md 29 KB
- reference/water-ocean.md 20 KB
- reference/webgl-pitfalls.md 1.9 KB
- techniques/ambient-occlusion.md 11 KB
- techniques/analytic-ray-tracing.md 19 KB
- techniques/anti-aliasing.md 4.5 KB
- techniques/atmospheric-scattering.md 18 KB
- techniques/camera-effects.md 3.4 KB
- techniques/cellular-automata.md 19 KB
- techniques/color-palette.md 13 KB
- techniques/csg-boolean-operations.md 15 KB
- techniques/domain-repetition.md 9.7 KB
- techniques/domain-warping.md 13 KB
- techniques/fluid-simulation.md 46 KB
- techniques/fractal-rendering.md 13 KB
- techniques/lighting-model.md 17 KB
- techniques/matrix-transform.md 12 KB
- techniques/multipass-buffer.md 34 KB
- techniques/normal-estimation.md 9.1 KB
- techniques/particle-system.md 45 KB
- techniques/path-tracing-gi.md 22 KB
- techniques/polar-uv-manipulation.md 13 KB
- techniques/post-processing.md 30 KB
- techniques/procedural-2d-pattern.md 11 KB
- techniques/procedural-noise.md 17 KB
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.
- 1mo ago First seen · 302 lines · 39 tokens per session scan A bfdece04db7d
shader-dev is a skill published in the GitHub repository bighardperson/computer-science-skills-collection (63 stars, last pushed 6mo ago), with no licence file. It adds 39 tokens to every session and 4,415 once invoked, about $0.0002 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
steam-publish
Publish or update a game on Steam with Steamworks and SteamPipe: configure depots and packages, upload builds with steamcmd, set a build live on a branch, and run the release checklists. Use for Steam publishing, appbuild.vdf/steamcmd uploads, depots, beta branches, or a store page release.
roblox-networking
Design and harden Roblox client/server networking with RemoteEvent, RemoteFunction, and UnreliableRemoteEvent; server authority, argument and Instance validation, rate limits, proximity/ownership checks, targeted replication, streaming, lifecycle, prediction, and reconciliation. Use for Roblox remotes, exploits…
roblox-ui
Build production Roblox interfaces with ScreenGui/PlayerGui lifecycle, responsive UDim2 layouts, safe insets, reusable editable Instances, cross-device input and selection, restrained motion, cleanup, and multi-viewport verification. Use for Roblox HUDs, inventories, shops, settings, ability bars, ScrollingFrames…
ebitengine-game
Create, improve, debug and package playable 2D games in Go with Ebitengine (github.com/hajimehoshi/ebiten/v2). Use for Ebitengine game requests: game design translated into a complete loop, input, rendering, text, audio, scenes, gameplay tests and desktop, browser or mobile builds. Also use when fixing these systems…
defold-core
Build and debug the core of a Defold game in Lua: game.project settings, collections, game objects and components, script lifecycle and self state, go.property, input focus and bindings, URLs and message passing, factories, collection factories and collection proxies, plus building and smoke-running with Bob. Use when…
ai-behavior-trees-utility-ai
Build a production behavior-tree runtime (Blackboard, action/condition leaves, sequence/selector/parallel composites, decorators) and a Utility AI system (response curves — linear, exponential, sigmoid, quadratic — considerations, and action evaluators), plus hybrid BT-drives-Utility agents. Use when implementing a…