Borrowing it
Nothing to install: this file belongs to plurigrid/asi. 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/plurigrid/asi/main/.claude/skills/deterministic-color-generation/SKILL.mdgit clone --depth 1 https://github.com/plurigrid/asiWrote 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/plurigrid/asi/deterministic-color-generation)<a href="https://agentmods.dev/skills/plurigrid/asi/deterministic-color-generation"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/deterministic-color-generation/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/plurigrid/asi/deterministic-color-generation"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/deterministic-color-generation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.02278 |
| Opus 5.5 | $0.00000 | $0.00911 |
| Sonnet 5.5 | $0.00000 | $0.00456 |
| Haiku 4.5 | $0.00000 | $0.00228 |
Grade A, and why
deterministic-color-generation 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 2mo 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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deterministic Color Generation via Metadata Hashing
Status: ✅ Production Ready Type: Color Space / Metadata Visualization Principle: Colors are NOT learned—they're deterministically computed from skill metadata Frame: Involution-invariant (ι∘ι = id) GF(3): Conservation verified across 4-level hierarchy
Core Discovery
Colors in IsUMAP visualization are NOT generated by any machine learning model.
Instead, they are deterministically computed from cryptographic hash functions applied to skill metadata:
skill_name → hash() → abs() % 0xFFFFFF → hex color (#RRGGBB)
Why This Matters
This approach is superior to ML-based alternatives because:
| Property | Hash-Based (Current) | ML-Based Alternatives |
|---|---|---|
| Determinism | 100% (no RNG) | 100% (with model) |
| Dependencies | None (Julia stdlib) | External packages |
| Reproducibility | Perfect (offline) | Good (model-dependent) |
| Transparency | ✓ Verifiable | ✗ Black box |
| Frame-Invariance | ✓ By design | ✗ Contingent |
| Complexity | Minimal | Substantial |
Color Generation Algorithm
4-Level Hierarchy
Level 0: World Color
├─ Input: All projects in world, sorted
├─ Hash: join(sort(projects), "|") → hash() → hex
└─ Property: Frame-invariant (project order irrelevant)
Level 1: Phase Color
├─ Input: Parent world color
├─ Hash: Inherited from Level 0
└─ Property: Trit differentiates phases (+1 or -1)
Level 2: Project Color
├─ Input: Project name
├─ Hash: hash(project_name) → hex
└─ Property: Group-level consistency
Level 3: Skill Color
├─ Input: Skill name
├─ Hash: hash(skill_name) → hex
└─ Property: Individual identity, deterministic
Implementation
# Julia code from GMRA_WORLDS_UNWORLDING.jl
# Level 0: World
projects_str = join(sort(projects), "|")
color_seed = abs(hash(projects_str)) % 0xFFFFFF
gay_color = string("#", lpad(string(color_seed, base=16), 6, "0"))
# Level 2: Project
project_hash = abs(hash(project)) % 0xFFFFFF
project_color = string("#", lpad(string(project_hash, base=16), 6, "0"))
# Level 3: Skill
skill_hash = abs(hash(skill_name)) % 0xFFFFFF
skill_color = string("#", lpad(string(skill_hash, base=16), 6, "0"))
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.
- 2mo ago First seen · 282 lines · 0 tokens per session scan A 0fb043d0c389
deterministic-color-generation is a skill published in the GitHub repository plurigrid/asi (72 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,278 tokens. 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 2026-09-01.
deterministic-color-generation compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| deterministic-color-generationplurigrid/asi | Skill | 72 | 7d ago | MIT | A | 0 | Claude Code |
| webgl-holographic-foilnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 41 | Claude Code, Codex |
| html-ppt-hermes-cyber-terminalnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 53 | Claude Code, Codex |
| html-ppt-taste-brutalistnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 78 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | 3d ago | MIT | A | 52 | Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 56 | Claude Code |
| accessibilitymicrosoft/hve-core | Skill | 1.6k | yesterday | MIT | A | 47 | Claude Code |