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 skills/jpeetz/agent-skills/har-api-reverse-engineeringnpx skills add JPeetz/agent-skills --skill har-api-reverse-engineeringgit clone --depth 1 https://github.com/JPeetz/agent-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/jpeetz/agent-skills/har-api-reverse-engineering)<a href="https://agentmods.dev/skills/jpeetz/agent-skills/har-api-reverse-engineering"><img src="https://agentmods.dev/badge/skills/jpeetz/agent-skills/har-api-reverse-engineering.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 | $0.00109 | $0.01391 |
| Opus 5 | $0.00055 | $0.00696 |
| Sonnet 5 | $0.00022 | $0.00278 |
| Haiku 4.5 | $0.00011 | $0.00139 |
Grade B, and why
har-api-reverse-engineering scanned grade B with 2 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- chmod 600 every HAR you keep; never commit one to a repo; never paste it (or the Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- curl 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 ships with it
4 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.
- 4d ago First seen · 117 lines · 109 tokens per session scan B 96ea8d4c81b6
har-api-reverse-engineering is a skill published in the GitHub repository JPeetz/agent-skills (5 stars, last pushed 4d ago), with no licence file. It adds 109 tokens to every session and 1,391 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, 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
web-reconstruction
Reconstruct a referenced website, page, interaction, or WebGL/WebGPU/Canvas effect from a URL or supplied evidence. Use for faithful site cloning, offline mirrors, responsive page replication, SPA fixture replay, visual-effect extraction, design transfer, and continued fidelity work on an existing replica. Not for…
tinyfish-integration
Integrate TinyFish web toolkit (search, fetch, browser automation) into Hermes Agent.
website-to-cli
Turn any website into a fast, beautiful command-line client. Use when the user wants a CLI that replicates a site's features by capturing its network traffic (HAR), recovering the private/undocumented API behind it, and generating a typed terminal client that calls those endpoints directly instead of driving a browser…
tests
Write clear, maintainable Vitest and Playwright tests with precise assertions, consistent structure, and strong behavioral coverage.
d3k
Use when the user asks to use d3k, run/dev/test/debug a web project with d3k, or reproduce a browser issue. Own the runtime: reuse or background-start d3k non-interactively, wait for readiness, use its project-stable managed Chrome profile, and inspect unified browser/server evidence.
verify
Drive an engine app headlessly in a pty, record a video of the whole verification, and open a summary page (video + timeline + checks) with pixel open.