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 eugenelim/agent-ready-repo --skill token-architecturegit clone --depth 1 https://github.com/eugenelim/agent-ready-repoWrote 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/eugenelim/agent-ready-repo/token-architecture)<a href="https://agentmods.dev/skills/eugenelim/agent-ready-repo/token-architecture"><img src="https://agentmods.dev/badge/skills/eugenelim/agent-ready-repo/token-architecture/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/eugenelim/agent-ready-repo/token-architecture"><img src="https://agentmods.dev/badge/skills/eugenelim/agent-ready-repo/token-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 304 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00086 | $0.03438 |
| Opus 5.5 | $0.00034 | $0.01375 |
| Sonnet 5.5 | $0.00017 | $0.00688 |
| Haiku 4.5 | $0.00009 | $0.00344 |
Grade A, and why
token-architecture 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.
How it starts
The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: token-architecture
Load this skill when the primary task is designing or auditing a token
system — the architecture that governs how tokens are named, derived, and
organized. Do not load this skill for routine surface work where seeding a
token block is sufficient; the fallback token block frontend-engineering routes to at its lowest authority rung
covers that case. Load token-architecture when:
- The product needs a token system designed from scratch
- An existing token system has hardcoded value drift and needs an audit
- A new semantic alias layer is being added (e.g., adding a dark-theme override)
- Multi-platform distribution requires DTCG-compatible source generation
Three-tier architecture
The one-way dependency rule governs the entire system:
Primitive → Semantic → Component
- Primitives are raw values:
#5e6ad2,16px,1.5. They have no meaning beyond their value. They are defined once at the top of the CSS file (or in the design tool) and referenced only by the semantic layer. Component tokens must not reference primitives directly — only semantics. - Semantics are role assignments:
--ds-color-primarypoints to a primitive. Semantics carry the design intent. When the brand changes, only the semantic layer's pointer changes; component tokens remain stable. - Components are usage tokens scoped to a specific component:
--btn-bg: var(--ds-color-primary). They reference semantics, never primitives.
Violation to refuse: a component token that reads
var(--primitive-color-indigo-500) directly. This is a one-way dependency
violation — if the primitive moves, every component that references it must
be updated rather than only the semantic pointer.
Naming conventions
The --ds- namespace prefix is required for all system tokens. It signals
"design system" and prevents collisions with author-defined custom properties
or third-party libraries.
Semantic naming rules
| Wrong | Right | Why |
|---|---|---|
--color-blue-500 |
--ds-color-primary |
Implementation detail leaks into the name; survives no redesign |
--spacing-16px |
--ds-space-4 |
Value leaks into the name; breaks if the scale changes |
--radius-8 |
--ds-radius-md |
Same problem; semantic size name is stable |
--font-inter |
--ds-font-body |
Font family leaks; semantic role is stable |
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.
- 1mo ago Changed fab689a5d289
- 2mo ago Changed · +45 tokens per session 06b7c4220f7f
- 2mo ago First seen · 322 lines · 41 tokens per session scan A 1685c6d4d337
token-architecture is a skill published in the GitHub repository eugenelim/agent-ready-repo (28 stars, last pushed yesterday), licensed Apache-2.0. It adds 86 tokens to every session and 3,438 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 2026-09-04.
token-architecture compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| token-architectureeugenelim/agent-ready-repo | Skill | 28 | yesterday | Apache-2.0 | A | 86 | Claude Code |
| moai-design-toolsmodu-ai/moai-adk | Skill | 1.3k | 4d ago | Apache-2.0 | A | 45 | Claude Code |
| moai-ref-ui-polishmodu-ai/moai-adk | Skill | 1.3k | 4d ago | Apache-2.0 | A | 98 | Claude Code |
| review-implementation-designdoordash-oss/agentic-orchestrator | Skill | 124 | 7d ago | Apache-2.0 | A | 13 | Claude Code, Codex |
| web-animation-css-animationsagents-inc/skills | Skill | 26 | 11d ago | MIT | A | 30 | Claude Code, Codex |
| figma-to-coded-htmlagnt-gg/agnt | Skill | 564 | 9d ago | none | A | 224 | Claude Code, Codex |
| high-end-website-designagnt-gg/agnt | Skill | 564 | 9d ago | none | B | 225 | Claude Code, Codex |