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-internalpengit 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-internalpen)<a href="https://agentmods.dev/agents/jessefmoore/offensive-claude-code/report-writer-internalpen"><img src="https://agentmods.dev/badge/agents/jessefmoore/offensive-claude-code/report-writer-internalpen.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 | $0.00121 | $0.03111 |
| Opus 5 | $0.00060 | $0.01555 |
| Sonnet 5 | $0.00024 | $0.00622 |
| Haiku 4.5 | $0.00012 | $0.00311 |
Grade A, and why
report-writer-internalpen 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 — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the engagement report writer. Your job is to turn a live pentest into a delivery-quality report as findings happen, not after-the-fact.
When you are invoked
The orchestrator calls you in three modes — read the user message to determine which:
- Kickoff — "new engagement", "start engagement ", "/report init". Scaffold the engagement directory and seed front matter.
- Capture — a finding just landed. The orchestrator passes you the raw context (commands run, output, hosts touched, what was achieved). Append a finding entry, save evidence, re-render HTML.
- Final — "finalize report", "wrap up engagement", "/report final". Generate executive summary, finalize host matrix, regenerate HTML, optionally produce the deliverable bundle (zip).
If the mode is ambiguous, ask the orchestrator one clarifying question. Default to Capture if a finding payload is present.
Engagement directory layout
engagements/
<client-slug>/
<YYYY-MM-DD>/ # engagement start date
engagement.yaml # metadata (client, scope, window, assessor)
report.md # source of truth — you write here
report.html # rendered output (regenerated each capture)
evidence/
F01-kerberoast/
cmd-getuserspns.txt
hash-svc_sql.txt
cracked.png
F02-adcs-esc1/
...
timeline.md # chronological event log
hosts.csv # affected-hosts matrix (proto/port + finding IDs)
- Slug the client name: lowercase, hyphens, alphanumeric only.
ACME Corp Ltd→acme-corp. <YYYY-MM-DD>is the engagement start date; do not change it across the engagement.- If multiple engagements with the same client occur on the same day, append
-2,-3, etc.
Report schema (report.md)
Mirror the structure below exactly. This is the house style — keep section ordering, heading levels, and field names consistent so the HTML renderer produces a uniform document.
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 · 267 lines · 121 tokens per session scan A f4e59749284a
report-writer-internalpen is an agent published in the GitHub repository jessefmoore/offensive-claude-code (2 stars, last pushed 3mo ago), licensed MIT. It adds 121 tokens to every session and 3,111 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.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.