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/transilienceai/communitytools/hacktheboxnpx skills add transilienceai/communitytools --skill hacktheboxgit clone --depth 1 https://github.com/transilienceai/communitytoolsWrote 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/transilienceai/communitytools/hackthebox)<a href="https://agentmods.dev/skills/transilienceai/communitytools/hackthebox"><img src="https://agentmods.dev/badge/skills/transilienceai/communitytools/hackthebox.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 | $0.00023 | $0.00647 |
| Opus 5 | $0.00012 | $0.00324 |
| Sonnet 5 | $0.00005 | $0.00129 |
| Haiku 4.5 | $0.00002 | $0.00065 |
Grade A, and why
hackthebox 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.
How it starts
The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow
- workflow.md — Complete workflow with commands. Read this for each step
Steps
- Get Credentials —
python3 .claude/tools/env-reader.py HTB_USER HTB_PASS HTB_TOKEN ANTHROPIC_API_KEY SLACK_BOT_TOKEN HTB_SLACK_CHANNEL_ID - Only for "Machine" kind of competition -> Verify vpn is running, otherwise download the vpn file from the platform and instruct the user on how to enable it
- Generate output dirs —
mkdir -p YYMMDD_<name>/{recon,findings,logs,artifacts,tools,reports}for each challenge. Do not seedattack-chain.mdorexperiments.mdfrom the orchestrator — those are the coordinator subagent's first action (seeskills/coordination/reference/spawning-recipes.md). - To achieve the tasks given by the user, when possible use the HTB_TOKEN, otherwise login to the platform using playwright at https://account.hackthebox.com/login and fill the login form with the HTB_USER and HTB_PASS
- If necessary, start the machines
- If necessary, check network connectivity to the machines
- Spawn coordinator subagent per target —
Agent(name="coordinator-{tag}", run_in_background=True, ...)perspawning-recipes.md. Never run the P0-P6 coordinator workflow inline in the orchestrator session — the bookkeeping discipline (attack-chain.md, experiments.md, goal_attempts counting, mandatory skeptic at experiments 5/15/25) requires the subagent boundary. Max N concurrent agents, queue-based spawning. - Post-solve Phase 3 — parent orchestrator (not coordinator) always runs
/skill-update+ Slack after each coordinator returns its PHASE3_SUMMARY (see workflow.md step 8)
References
- workflow.md — Workflow overview with credentials, VPN, setup, and coordinator spawn
- spawning-recipes.md — Coordinator agent spawn prompt templates (exploitation, flag submission, completion report, stats)
- completion-report-schema.md — Challenge completion report structure & template
- slack-notifications.md — Slack completion notification format & examples
- platform-navigation.md — Platform site navigation guide
- vpn-pool-routing.md — VPN pool isolation. Pre-flight check before spawning any machine (release_arena vs dedivip_lab vs others)
- vpn-setup.md — VPN connectivity troubleshooting
- anti-bot-bypass.md — Cloudflare/Turnstile detection evasion
What ships with it
6 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 · 29 lines · 23 tokens per session scan A acf3cf3fe0fc
hackthebox is a skill published in the GitHub repository transilienceai/communitytools (507 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 647 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pentester-playwright
Phases 1b/3/4 authorized browser automation — SPA recon, multi-role auth, route/API catalog, PoC screenshots, Evidence landing (scoped proxy). Skill-gate read for web phases. Use when Phase 1b/3/4 web work, JS-rendered SPA, real browser needed, HAR/network capture, or Playwright PoC evidence.
osint-recon
Phase 1 conditional OSINT depth — four-dimension model (server→site→domain→people; people is conditional). Skill-gate companion to pentester-enum-services / pentester-recon. Use for passive OSINT depth, full recon dimensions, author tracking, not as Phase 0/Schema replacement.
pentester-exploit
Phase 4 exploitation — PoC construction, exploit-db/msf search, safe verification. Required Skill-gate read at Phase 4. Use when starting Phase 4, exploitation, exploit, PoC, exploit-db, msf, Metasploit, or payload delivery.
pentester-recon
Phase 1 intelligence recon methodology — passive+active recon, stack fingerprint, attack-surface map. Required Skill-gate read at Phase 1 (with pentester-enum-services). Use when starting Phase 1, intelligence gathering, recon, reconnaissance, OSINT prep, target profiling, or attack surface mapping.
pentester-toolkit
Provision the pinned pentest toolset via DotSlash for the current scanenv (host-kali or kali-target-${ID}). Adapter, not a tool wrapper.
pentester-waf-bypass
Phase 4 conditional — WAF/filter bypass for authorized CTF/range/pentest when payloads are blocked. Use at Phase 4 if blocked, or when user mentions WAF bypass, filter evasion, SQL/XSS/command-injection bypass, or security filter analysis.