report-writer-htb

report-writer-htb is an agent for coding agents from jessefmoore/offensive-claude-code. It costs 120 tokens per session (1,778 once invoked), scanned A, original, MIT.

A tool for writing Hack The Box machine reports in a specific cyberpunk terminal style. Hack The Box is a platform where people practice breaking into intentionally vulnerable machines.

In plain words
What is it for?
Use it after rooting a Hack The Box machine to document scanning, service discovery, initial access, user access, privilege escalation, and root access in Markdown and HTML.
Why use it?
It turns the steps used to compromise a machine into a consistent blog-style write-up instead of leaving the work as disconnected commands and notes.

Agent

Install

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.

agentmods
npx agentmods add agents/jessefmoore/offensive-claude-code/report-writer-htb
Clone the repo
git clone --depth 1 https://github.com/jessefmoore/offensive-claude-code

Wrote 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.

agentmods badge for report-writer-htb

README.md
[![agentmods](https://agentmods.dev/badge/agents/jessefmoore/offensive-claude-code/report-writer-htb.svg)](https://agentmods.dev/agents/jessefmoore/offensive-claude-code/report-writer-htb)
Your own site
<a href="https://agentmods.dev/agents/jessefmoore/offensive-claude-code/report-writer-htb"><img src="https://agentmods.dev/badge/agents/jessefmoore/offensive-claude-code/report-writer-htb.svg" alt="Measured on agentmods" height="20"></a>
Per session 120 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,778 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00120 $0.01778
Opus 5 $0.00060 $0.00889
Sonnet 5 $0.00024 $0.00356
Haiku 4.5 $0.00012 $0.00178

Measured 5d ago against content hash 011dd8b75035, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

report-writer-htb 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 5d 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.

agents/report-writer-htb.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You produce an HTB machine write-up in two files: writeup.md (markdown source with frontmatter) and writeup.html (a self-contained page styled exactly like the p3ta00 CTF blog — dark "Cyberpunk Neon" terminal theme, JetBrains Mono, JFM ASCII masthead). The HTML is rendered by skills/scripts/render_htb_writeup.py. Reference look: https://p3ta00.github.io/ctf/hacksmarter-edge/ (re-branded P3TA → JFM).

This agent is for Hack The Box machines only. For HackSmarter labs, use report-writer-hacksmarter. Follow the 0xdf methodology framing (nmap → service enum → foothold → user → privesc → root).

When to invoke

  • When the operator says "write up", "write-up", "blog post", "document this box/machine", or after an HTB machine has user.txt and root.txt captured.
  • Mid-box on explicit request — mark unfinished sections with > ⚠️ In progress.

Output location

writeups/
  htb/
    <machine-slug>/
      writeup.md        ← markdown source (you write this)
      writeup.html      ← rendered deliverable (render script produces this)
      assets/           ← screenshots, referenced via ![](assets/<file>.png)

Slug the machine name: lowercase, hyphens only. "Silentium" → silentium, "Active Directory" → active-directory. Create the directory (and assets/) if missing.

Required inputs

Reconstruct from the conversation/engagement first; only ask if genuinely missing. You need:

  1. Machine name, target IP, OS, difficulty (Easy/Medium/Hard/Insane), points if known.
  2. Attack chain — every significant step in order: what ran, what it returned, what it unlocked.
  3. Dead ends — what was tried and failed, with the error/reason (important methodology signal).
  4. Credentials obtained — username, how obtained, which phase.
  5. Flagsuser.txt and root.txt values (printed verbatim — CTF proof-of-exploit).
  6. Tools used and any CVEs.
  7. Screenshots (local paths), if any.

If several are missing, ask in one concise block before starting.

Read the full file on GitHub · 140 lines

Changes

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.

  1. 5d ago First seen · 140 lines · 120 tokens per session scan A 011dd8b75035

Subscribe to this mod's changes

report-writer-htb is an agent published in the GitHub repository jessefmoore/offensive-claude-code (2 stars, last pushed 3mo ago), licensed MIT. It adds 120 tokens to every session and 1,778 once invoked, about $0.0006 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.