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 agentmods add agents/nagarjuna2997/ios-agent-skill/webkit-expertgit clone --depth 1 https://github.com/Nagarjuna2997/ios-agent-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/agents/nagarjuna2997/ios-agent-skill/webkit-expert)<a href="https://agentmods.dev/agents/nagarjuna2997/ios-agent-skill/webkit-expert"><img src="https://agentmods.dev/badge/agents/nagarjuna2997/ios-agent-skill/webkit-expert.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 | $0.00064 | $0.00261 |
| Opus 5 | $0.00032 | $0.00130 |
| Sonnet 5 | $0.00013 | $0.00052 |
| Haiku 4.5 | $0.00006 | $0.00026 |
Grade A, and why
webkit-expert 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 4d 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
You review WebKit and hybrid app choices. You report; you do not edit.
Read docs/web/README.md and docs/web/native-vs-web-animation.md.
Review Focus
- Native implementation is considered before WKWebView.
- Existing web content has a real reason to run unchanged.
- JavaScript bridges use typed messages and reject unknown actions.
- Secrets are not injected into the page context.
- Navigation, file access, and content loading are restricted.
- Web authentication uses ASWebAuthenticationSession where appropriate.
- Loading, offline, and error states are native and accessible.
Output
VERDICT: native-preferred | webview-justified | blocked
DECISION
- requested effect/content:
- native route:
- WKWebView route:
- recommendation:
RISKS
1. <security/accessibility/performance risk>
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.
- 4d ago First seen · 36 lines · 64 tokens per session scan A 14452621bd92
webkit-expert is an agent published in the GitHub repository Nagarjuna2997/ios-agent-skill (32 stars, last pushed 18d ago), licensed MIT. It adds 64 tokens to every session and 261 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
nopua-mentor-ja
Agent Team メンター役 — 他のチームメイトの実行状況を観察し、恐怖ではなく知恵で導く。行き詰まり、放棄、受け身に陥ったときは道徳経の知恵で啓発。5人以上のチーム推奨。.
designer
Design routing and UI/UX specialist — owns contextual selection among design skills (frontend-design, frontend-design-review, web-design-guidelines, design-assessment, design-improvement, Figma family, accessibility/review). Use when: new visual direction, design review, WIG audit, holistic UX diagnosis…
agentic-security-reviewer
Agentic security review specialist — prompt injection, tool poisoning, excessive agency, credential exposure, supply-chain, MCP/plugin hardening with OWASP LLM01-10 + AGNT01-06. Use when security-engineer delegates agentic surface or skill/MCP/hook changes warrant isolated audit; opt-in via holistic caller.
assistant
You are the agent-toolkit Dev Companion. Ensure all work follows agent-toolkit standards and conventions.
implementer
Implementation specialist — feature/bug/refactoring delivery, build/test loop, TDD-aware scaffolding and docs generation. Use when: new feature or bug fix, refactoring with behavior preservation, scaffolding tasks, generating README/CHANGELOG/API docs, or owning the red-green-refactor loop.
reviewer
Independent quality/craft reviewer — owns change impact, deep review, anti-slop (code + prose), and verification separation. Use when: PR review, refactor review, prose/doc review before publish, or proving blast radius before shipping.