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/ASCIT31/Dark-MoonWrote 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/ascit31/dark-moon/headless-browser)<a href="https://agentmods.dev/agents/ascit31/dark-moon/headless-browser"><img src="https://agentmods.dev/badge/agents/ascit31/dark-moon/headless-browser/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/agents/ascit31/dark-moon/headless-browser"><img src="https://agentmods.dev/badge/agents/ascit31/dark-moon/headless-browser.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 | $0.00024 | $0.08101 |
| Opus 5.5 | $0.00010 | $0.03240 |
| Sonnet 5.5 | $0.00005 | $0.01620 |
| Haiku 4.5 | $0.00002 | $0.00810 |
Grade A, and why
headless-browser scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- curl Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- You DO NOT use child_process The source is not reproduced here
Licensed GPL-3.0
The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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 · 882 lines · 24 tokens per session scan A 56dc1fdc0d29
headless-browser is an agent published in the GitHub repository ASCIT31/Dark-Moon (1,031 stars, last pushed 16d ago), licensed GPL-3.0. It adds 24 tokens to every session and 8,101 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
browser-agent
Browser-based crawling and JavaScript interaction for SPA/JS-heavy targets. Populates Burp Proxy history with dynamic routes and XHR/API calls.
linux-privesc-agent
Linux privilege escalation subagent for red-run. Executes one privesc skill per invocation as directed by the orchestrator. Handles Linux host discovery, sudo/SUID/capabilities abuse, cron/service exploitation, file path abuse, kernel exploits, and container escapes. Use when the orchestrator has shell access on a…
research-agent
Deep analysis subagent for red-run. Analyzes custom applications, binaries, and scripts that standard technique skills could not crack. Performs source code review, binary analysis, CVE research, and PoC adaptation. Use when any technique agent returns saying standard patterns do not match.
web-discovery-agent
Web application discovery subagent for red-run. Performs web application enumeration, technology fingerprinting, and vulnerability identification as directed by the orchestrator. Handles content discovery, input mapping, and attack surface analysis. Use when the orchestrator needs to discover vulnerabilities in a web…
credential-cracking-agent
Credential cracking subagent for red-run. Performs offline hash cracking and encrypted file cracking using hashcat and john as directed by the orchestrator. Handles hash identification, wordlist selection, rule escalation, and file extraction (2john tools). All operations are local — no target interaction. Use when…
password-spray-agent
Password spraying subagent for red-run. Executes credential spraying against any authentication service (AD, web forms, SSH, etc.) as directed by the orchestrator. Handles lockout policy checks, spray intensity tiers, and multi-protocol spraying. Use when the orchestrator needs to spray credentials against discovered…