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 veelenga/preview-skills --skill preview-jsongit clone --depth 1 https://github.com/veelenga/preview-skillsWrote 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/veelenga/preview-skills/preview-json)<a href="https://agentmods.dev/skills/veelenga/preview-skills/preview-json"><img src="https://agentmods.dev/badge/skills/veelenga/preview-skills/preview-json.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 | $0.00021 | $0.01188 |
| Opus 5 | $0.00010 | $0.00594 |
| Sonnet 5 | $0.00004 | $0.00238 |
| Haiku 4.5 | $0.00002 | $0.00119 |
Grade A, and why
preview-json 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 8d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preview JSON Skill
Interactive JSON/JSONL viewer that generates HTML visualizations with syntax highlighting, collapsible tree structure, and search functionality.
Agent Usage
When the user asks to preview a JSON or JSONL file, DO NOT build HTML manually. Use the Bash tool to execute this skill's run.sh script:
# Preview a JSON file
./run.sh data.json
# Preview a JSONL file
./run.sh logs.jsonl
# Pipe content
cat data.json | ./run.sh
The script handles all HTML generation and automatically opens the result in the browser. Do NOT open the file manually to avoid duplicate tabs.
Usage
# Preview a JSON file
/preview-json data.json
# Preview a JSONL file (JSON Lines format)
/preview-json logs.jsonl
# Pipe JSON data (preferred for temporary content)
cat data.json | /preview-json
echo '{"name":"test","value":123}' | /preview-json
# Pipe JSONL data
echo '{"id":1,"name":"Alice"}
{"id":2,"name":"Bob"}' | /preview-json
# With custom background color
/preview-json data.json --background "#1e1e1e"
Best Practice: For temporary or generated content, prefer piping over creating temporary files. This avoids cluttering your filesystem and the content is automatically cleaned up.
Options
The script works with sensible defaults but supports these flags for flexibility:
-o, --output PATH- Custom output path--no-browser- Skip browser, output file path only
Features
- Syntax highlighting with color-coded types:
- Strings (green)
- Numbers (blue)
- Booleans (orange)
- Null values (red)
- Keys (purple)
- Collapsible tree view for nested structures
- Search through keys and values in real-time
- Copy values to clipboard with one click
- Pretty formatted with proper indentation
- Type indicators for each value
- Line numbers for easy reference
- Responsive design adapts to screen size
When to Use This Skill
Use this skill when the user wants to:
- View and explore JSON data files
- View JSONL (JSON Lines) log files or streaming data
- Inspect API responses
- Debug JSON structures
- Verify JSON formatting
- Share formatted JSON data
- Analyze newline-delimited JSON exports
What ships with it
11 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.
- config.sh 553 B runs code
- lib/browser-utils.sh 9.5 KB runs code
- lib/content-utils.sh 6.7 KB runs code
- lib/html-generator.sh 14 KB runs code
- run.sh 7.5 KB runs code
- templates/scripts/common-ui.js 5.1 KB runs code
- templates/scripts/json-renderer.js 11 KB runs code
- templates/scripts/utils.js 1.8 KB runs code
- templates/styles/common.css 1.6 KB
- templates/styles/json.css 2.7 KB
- templates/styles/layout.css 14 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.
- 8d ago First seen · 206 lines · 21 tokens per session scan A cf266c2ff93e
preview-json is a skill published in the GitHub repository veelenga/preview-skills (8 stars, last pushed 28d ago), licensed MIT. It adds 21 tokens to every session and 1,188 once invoked, about $0.0001 per session on Opus 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.
Other skills, from other repositories
agent-browser
A command-line browser automation tool for AI agents. It can navigate websites and operate Electron desktop applications, using a compact view of page controls and their references.
twitter-watch
A workflow for collecting interaction data from a series of Twitter posts and combining it into a report. It uses a visible, persistent browser session so an already logged-in Twitter account can be reused.
browser-testing
A browser-based end-to-end testing workflow, where end-to-end testing means checking a complete user-facing feature through the browser, with test cases stored in Markdown files.
playwright-best-practices
Use when writing Playwright tests, fixing flaky tests, debugging failures, implementing Page Object Model, configuring CI/CD, optimizing performance, mocking APIs, handling authentication or OAuth, testing accessibility (axe-core), file uploads/downloads, date/time mocking, WebSockets, geolocation, permissions…
firecrawl-search
Web search with full page content extraction. Use this skill whenever the user asks to search the web, find articles, research a topic, look something up, find recent news, discover sources, or says "search for", "find me", "look up", "what are people saying about", or "find articles about". Returns real search…
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.