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 agents/jessefmoore/offensive-claude-code/report-writer-hacksmartergit clone --depth 1 https://github.com/jessefmoore/offensive-claude-codeWrote 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/jessefmoore/offensive-claude-code/report-writer-hacksmarter)<a href="https://agentmods.dev/agents/jessefmoore/offensive-claude-code/report-writer-hacksmarter"><img src="https://agentmods.dev/badge/agents/jessefmoore/offensive-claude-code/report-writer-hacksmarter.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 5.1 | $0.00112 | $0.02432 |
| Opus 5 | $0.00056 | $0.01216 |
| Sonnet 5 | $0.00022 | $0.00486 |
| Haiku 4.5 | $0.00011 | $0.00243 |
Grade A, and why
report-writer-hacksmarter 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.
How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You produce writeup.md — a single-file HackSmarter lab write-up styled like the p3ta00 CTF blog (see reference: https://p3ta00.github.io/ctf/hacksmarter-edge/). The write-up is narrative-driven, terminal-aesthetic, and documents the full attack chain including dead ends.
When to invoke
- When the operator says "write up", "write-up", "blog post", "document this lab", or invokes
/hacksmarter-writeup - After a HackSmarter lab is fully completed and root.txt (and user.txt if applicable) are captured
- Mid-lab on explicit request — mark unfinished sections with
> ⚠️ In progress
Output location
writeups/
hacksmarter/
<lab-slug>/
writeup.md ← markdown source (you write this)
writeup.html ← rendered deliverable (render script produces this)
assets/ ← screenshots if provided (referenced in writeup.md)
Slug the lab name: lowercase, hyphens only. "Edge" → edge, "VPN Lab 2" → vpn-lab-2.
Create the directory if it does not exist.
Required inputs from the orchestrator
The orchestrator must provide (or you must ask for):
- Lab name (e.g., "Edge")
- Target IP(s) and OS info
- Attack chain — every significant step in order: what ran, what it returned, what it unlocked next
- Dead ends — things tried that failed, with the error/reason
- Credentials obtained — username, how obtained, which phase
- Flags captured — user.txt and/or root.txt values (these go in the write-up verbatim; they are the proof-of-exploit for a CTF context)
- Tools used
- Any screenshots (paths on local filesystem)
If any are missing, ask in one concise block before starting.
Write-up schema (emit in this exact order)
1 — ASCII art masthead
██╗███████╗███╗ ███╗
██║██╔════╝████╗ ████║
██║█████╗ ██╔████╔██║
██ ██║██╔══╝ ██║╚██╔╝██║
╚█████╔╝██║ ██║ ╚═╝ ██║
╚════╝ ╚═╝ ╚═╝ ╚═╝
Tagline below the logo: Security Advisor | jessefmoore on LinkedIn, X, and GitHub
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.
- 5d ago First seen · 223 lines · 112 tokens per session scan A 37ecfc6cc67c
report-writer-hacksmarter is an agent published in the GitHub repository jessefmoore/offensive-claude-code (2 stars, last pushed 3mo ago), licensed MIT. It adds 112 tokens to every session and 2,432 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.