Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/fellipeutaka/leonnpx agentmods add skills/fellipeutaka/leon/denjiWrote 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/fellipeutaka/leon/denji)<a href="https://agentmods.dev/skills/fellipeutaka/leon/denji"><img src="https://agentmods.dev/badge/skills/fellipeutaka/leon/denji/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/fellipeutaka/leon/denji"><img src="https://agentmods.dev/badge/skills/fellipeutaka/leon/denji.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 | $0.00106 | $0.02902 |
| Opus 5.5 | $0.00042 | $0.01161 |
| Sonnet 5.5 | $0.00021 | $0.00580 |
| Haiku 4.5 | $0.00011 | $0.00290 |
Grade A, and why
denji 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 — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Managing SVG Icons with Denji
Denji converts Iconify SVG icons into typed framework components. Icons are fetched, optimized (SVGO), and generated as native components for your framework.
Core Workflow
# 1. Initialize project
npx denji init --framework react --output ./src/icons.tsx
# 2. Add icons (prefix:name format from Iconify)
npx denji add lucide:check lucide:x lucide:arrow-right
# 3. Use in your code
import { Icons } from "./icons";
<Icons.Check className="size-4 text-green-500" />
<Icons.X className="size-4 text-red-500" />
Commands
denji init
Initialize a Denji project. Creates denji.json config and icons template.
npx denji init
npx denji init --framework react --output ./src/icons.tsx
npx denji init --framework svelte --output ./src/icons --output-type folder
npx denji init --framework react --no-typescript --output ./src/icons.jsx
npx denji init --a11y hidden --forward-ref
| Flag | Description |
|---|---|
--framework <name> |
react, preact, solid, qwik, vue, svelte |
--output <path> |
Output path for icons file/folder |
--output-type <type> |
file (single file) or folder (one file per icon) |
--typescript / --no-typescript |
TypeScript or JavaScript (default: TS) |
--a11y <strategy> |
hidden, img, title, presentation, or false (no a11y attrs) |
--forward-ref / --no-forward-ref |
Use forwardRef (React/Preact only) |
--track-source / --no-track-source |
Track Iconify source via data-icon attr |
-c, --cwd <path> |
Working directory |
Missing flags trigger interactive prompts.
denji add <icons...>
Add icons from Iconify. Icons use prefix:name format.
npx denji add lucide:check
npx denji add lucide:check mdi:home radix-icons:cross-2
npx denji add lucide:star --name FavoriteStar
npx denji add lucide:info --a11y img
# Preview without writing files
npx denji add lucide:check mdi:home --dry-run
| Flag | Description |
|---|---|
--name <name> |
Custom component name (single icon only) |
--a11y <strategy> |
Override a11y strategy for this icon |
--dry-run |
Preview what would be generated without writing any files |
-c, --cwd <path> |
Working directory |
What ships with it
3 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.
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 · 371 lines · 106 tokens per session scan A 9789f9247b23
denji is a skill published in the GitHub repository fellipeutaka/leon (5 stars, last pushed yesterday), licensed MIT. It adds 106 tokens to every session and 2,902 once invoked, about $0.0004 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 2026-08-31.
denji compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| denjifellipeutaka/leon | Skill | 5 | yesterday | MIT | A | 106 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |