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 jcrabapple/hermes-skills --skill browser-tool-failuresgit clone --depth 1 https://github.com/jcrabapple/hermes-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/jcrabapple/hermes-skills/browser-tool-failures)<a href="https://agentmods.dev/skills/jcrabapple/hermes-skills/browser-tool-failures"><img src="https://agentmods.dev/badge/skills/jcrabapple/hermes-skills/browser-tool-failures/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/jcrabapple/hermes-skills/browser-tool-failures"><img src="https://agentmods.dev/badge/skills/jcrabapple/hermes-skills/browser-tool-failures.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 | $0.00086 | $0.02006 |
| Opus 5 | $0.00043 | $0.01003 |
| Sonnet 5 | $0.00017 | $0.00401 |
| Haiku 4.5 | $0.00009 | $0.00201 |
Grade A, and why
browser-tool-failures scanned grade A 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -w "%{http_code}\n" -o /dev/null --max-time 3 http://localhost:9377/health The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 10d ago First seen · 140 lines · 86 tokens per session scan A b5c196b2ac90
browser-tool-failures is a skill published in the GitHub repository jcrabapple/hermes-skills (10 stars, last pushed 11d ago), with no licence file. It adds 86 tokens to every session and 2,006 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
especialista-em-debug
Diagnóstico sistemático de bugs: análise de logs, stack traces, reprodução do problema e estratégia de fix. Framework step-by-step para encontrar e resolver qualquer tipo de bug em aplicações web, mobile ou backend.
external-gitcode-ascend-atb-debug-guide
A troubleshooting guide for ATB operator tests and Ascend NPU environments. It covers issues such as ABI mismatches, memory errors, failed CSV tests, and ACLNN interface problems.
troubleshooting
A troubleshooting guide for Kubernetes, a system for running containerized applications across computers. It lists commands for checking clusters, nodes, components, pods, events, resources, and storage.
quarkus-debug
Expert skill for deep debugging of Quarkus applications, covering Dev Mode, Reactive patterns (Mutiny), Native Image (AOT) issues, and Build-time (Augmentation) troubleshooting.
systematic-debugging
A four-stage method for debugging software: reproduce the problem, narrow down where it occurs, find the root cause, and verify a focused fix.
windows-update-troubleshooting
Use when hermes update fails, defers, or loops on Windows.