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.
git clone --depth 1 https://github.com/widnyana/eyay-toolkitsWrote 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/commands/widnyana/eyay-toolkits/dt)<a href="https://agentmods.dev/commands/widnyana/eyay-toolkits/dt"><img src="https://agentmods.dev/badge/commands/widnyana/eyay-toolkits/dt.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 | $0.00026 | $0.00534 |
| Opus 5 | $0.00013 | $0.00267 |
| Sonnet 5 | $0.00005 | $0.00107 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade B, and why
dt scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Current state: !`test -f .claude/design-thinking.local.md && cat .claude/design-thinking.local.md || echo "(no state file — enabled: false)"` What it actually says
Argument: $ARGUMENTS
State file: .claude/design-thinking.local.md — YAML frontmatter
enabled: true|false, e.g.:
---
enabled: true
---
Current state: !test -f .claude/design-thinking.local.md && cat .claude/design-thinking.local.md || echo "(no state file — enabled: false)"
Do the following:
- Read the
enabledvalue from the state shown above. Treat it asfalseif the file doesn't exist. - Classify the argument (case-insensitive, trimmed):
- Empty → toggle: flip
enabled. on→ setenabled: true.off→ setenabled: false.status→ do not write anything. Report "Design Thinking mode: on" or "Design Thinking mode: off" and stop here.- Anything else → set
enabled: true(never off, regardless of current state) and remember the full argument text as<prompt>for step 5.
- Empty → toggle: flip
- Unless the branch was
status, write the new value to.claude/design-thinking.local.md(create the.claude/directory first if it doesn't exist) using exactly this format:--- enabled: <true|false> --- - Notify the user of the resulting mode:
- Turned on: "Design Thinking ON — plans and reviews will render as Design Graphs (Graph Protocol)."
- Turned off: "Design Thinking OFF."
- If step 2 captured a
<prompt>, continue in this same turn: work on<prompt>, but first present the Design Graph (Graph Protocol format — see this plugin'sgraph-protocol,design-method, anddesign-graphskills) plus any clarifying questions. Implement only after the user's go-ahead.
Design Thinking mode persists across restarts via the state file above: this
plugin's SessionStart hook re-announces the mode at the start of every new
session while enabled: true. Turn it off any time with /dt off.
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 · 52 lines · 26 tokens per session scan B ba0ceb9389ed
dt is a command published in the GitHub repository widnyana/eyay-toolkits (7 stars, last pushed 5d ago), licensed MIT. It adds 26 tokens to every session and 534 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
design-audit
Audit an existing HTML/CSS design. Deterministic checks only (contrast, fonts, colors, states, dark mode) plus a visual pass. No generation.
design-component
Generate a single component using existing design-system.md tokens. Skips inspiration browsing — fast path for isolated UI elements.
design-mobile
Design a mobile screen or flow. This command never writes SwiftUI or Compose — the deliverable is a device-framed HTML mockup plus a handoff spec for the platform developer.
design
Full design pipeline for a web or web-app target: brief → tokens → generation → motion → review. Use /design:mobile for iOS/Android instead.
design-page
New page or screen in an existing project. Skips design-system creation — reuses the existing design-system.md tokens.
summary
Generate a consolidated project brief from design artifacts. For the full spec package with YAML specs and validation, use /compile instead.