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/yaniv-golan/pretext-skillWrote 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/plugins/yaniv-golan/pretext-skill/pretext)<a href="https://agentmods.dev/plugins/yaniv-golan/pretext-skill/pretext"><img src="https://agentmods.dev/badge/plugins/yaniv-golan/pretext-skill/pretext/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/plugins/yaniv-golan/pretext-skill/pretext"><img src="https://agentmods.dev/badge/plugins/yaniv-golan/pretext-skill/pretext.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
pretext 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.
What it actually says
{
"name": "pretext",
"version": "0.2.2",
"description": "AI skill for @chenglou/pretext — a small, tree-shakable TypeScript text measurement library that computes exact text metrics without DOM reflows",
"author": {
"name": "Yaniv Golan",
"email": "[email protected]"
},
"repository": "https://github.com/yaniv-golan/pretext-skill",
"license": "MIT",
"keywords": ["pretext", "text-measurement", "text-layout", "canvas", "typography", "reflow-free"],
"skills": "./skills"
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 182 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 First seen · 14 lines scan A 35f89fed064a
pretext is a plugin published in the GitHub repository yaniv-golan/pretext-skill (15 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.
Other plugins, from other repositories
sui-dev-tools
Sui blockchain development skills — Move smart contracts, TypeScript SDK, frontend dApp Kit, Seal secrets, and Walrus storage.
typescript-rules
TypeScript coding conventions with automatic validation, review command, and reviewer agent.
carloshpdoc-plugins marketplace
iOS-opinionated Claude Code workflow automation: Swift 6 migration, Apollo to native SDK removal, stacked PRs, Jira integration, Xcode build optimization.
ios-workflow
iOS workflow automation: Swift 6 migration, Apollo to native SDK removal, stacked PRs via gh CLI, Jira-driven PR opener, feature-flag cleanup, perf playbook, SwiftLint fixer. Project-specific values are auto-detected or asked at runtime - no setup required.
xcode-build-suite
End-to-end Xcode build-time optimization: benchmark, analyze (compile/project/SPM), recommend, apply with approval, then re-benchmark.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.