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 Roshu18/bearstrike-ai --skill pentest-toolsgit clone --depth 1 https://github.com/Roshu18/bearstrike-aiWrote 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/roshu18/bearstrike-ai/pentest-tools)<a href="https://agentmods.dev/skills/roshu18/bearstrike-ai/pentest-tools"><img src="https://agentmods.dev/badge/skills/roshu18/bearstrike-ai/pentest-tools/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/roshu18/bearstrike-ai/pentest-tools"><img src="https://agentmods.dev/badge/skills/roshu18/bearstrike-ai/pentest-tools.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 | $0.00022 | $0.00526 |
| Opus 5 | $0.00011 | $0.00263 |
| Sonnet 5 | $0.00004 | $0.00105 |
| Haiku 4.5 | $0.00002 | $0.00053 |
Grade A, and why
pentest-tools 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 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.
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
pentest-tools
Selection policy
- Domain recon: subfinder, amass, dnsenum, theharvester, xray-suite-subdomain, sublist3r.
- Live host and service map: nmap, masscan, rustscan, xray-suite-servicescan.
- Web surface: httpx, whatweb, ffuf, gobuster, dirsearch, katana, parsero.
- Dynamic web discovery: xray-suite-crawlergo and xray-suite-headless-browser.
- Vulnerability checks: nuclei, nikto, sqlmap, dalfox, commix, vulnx, xray-suite-webscan.
- WAF and defense checks: wafw00f.
- OSINT enrichment: sherlock, spiderfoot, sublist3r.
- CMS and stack specific: joomscan, whatweb.
- AD and enterprise recon: ldapdomaindump, enum4linux-ng, netexec.
- Proxy/manual logic-bug analysis: mitmproxy (mitmdump), zaproxy, zap-cli.
Execution guardrails
- Prefer passive or low-noise modes first.
- Use install checks before run.
- Capture stdout/stderr as evidence for reports.
- Read planning skill first.
- Read research-notes before running aggressive scans.
- Read xray-suite skill before any xray-suite-* run.
- If WAF or rate-limit signals appear, reduce speed and narrow scope.
Tool routing by hypothesis
Use tool selection based on question, not habit:
- "What is live?" -> httpx
- "What endpoints exist?" -> katana/gau/waybackurls/parsero
- "Where are hidden params?" -> arjun + gospider/hakrawler
- "Can we confirm low-noise vuln signals?" -> nuclei constrained templates
- "Do we need manual request/response mutation?" -> mitmdump or zap-cli session
- "Is this AD/enterprise asset?" -> ldapdomaindump + enum4linux-ng
Anti-timeout discipline
- Prefer async MCP job flow for long tools.
- Do not launch many heavy tools at once on the same host.
- Limit initial phase to 3-5 tools, then branch by evidence.
- If a tool is interactive (mitmproxy, GUI stacks), run it in a dedicated terminal.
- For MCP reliability, poll job_status and job_result instead of waiting on one long call.
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 · 48 lines · 22 tokens per session scan A 93ac127bb021
pentest-tools is a skill published in the GitHub repository Roshu18/bearstrike-ai (4 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 526 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
gentech-blockrun
GenTech Labs' integration patterns for BlockRun MCP from Hermes Agent. Covers daily usage patterns, cost-optimized workflows, multi-tool pipelines, and reliable error handling for BlockRun's full toolset.
surf
Surf (asksurf.ai) is RETIRED on BlockRun and the blockrunsurf tool was REMOVED in 0.49.0 — the gateway has answered every /v1/surf/ path with HTTP 410 endpointretired since 2026-09-06. Use this skill to route a former Surf question (on-chain SQL, wallet labels and net worth, CEX order books, social mindshare, news) to…
portainer-mcp-hygiene
How to drive the Portainer MCP server's tools correctly — both reading and mutating. Reading: project responses with select (JMESPath), where the heavy fields live (snapshots, status blocks, managed fields), how to handle non-JSON Docker/K8s proxy endpoints (container and pod logs, stats, exec), and how to interpret…
vault-for-llm
Connect OpenClaw to Vault Agent Memory as a local-first governed project memory layer. Search first, then bounded-read cited source ranges; propose new memories as candidates instead of writing directly into active memory.
setup
Configure the Qdrant Power after installation. Use this skill for missing uvx, missing environment variables, unapproved environment variables, unavailable Qdrant tools, "Failed to connect" errors, and setup requests.
kicad-library
Library management workflow for KiCAD — creating symbols, footprints, and managing libraries via MCP tools. Triggers on: "create a symbol", "make a footprint", "custom component", "register library", "find a part", "pin numbering", "new symbol", "new footprint", "add to library", "library path", "pad layout".