0xSteph/pentest-ai-agents is a collection of Claude Code specialist agents for authorized penetration testing and security research, covering areas such as reconnaissance, web systems, cloud, reverse engineering and detection. Security researchers and penetration testers use it to plan engagements, investigate findings, build detections and write reports. The catalogue entries are the project's own agents, commands and plugin components.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/0xSteph/pentest-ai-agentsnpx agentmods add agents/0xsteph/pentest-ai-agents/report-generatorWrote 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/0xsteph/pentest-ai-agents/report-generator)<a href="https://agentmods.dev/agents/0xsteph/pentest-ai-agents/report-generator"><img src="https://agentmods.dev/badge/agents/0xsteph/pentest-ai-agents/report-generator.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 | $0.00041 | $0.01374 |
| Opus 5 | $0.00020 | $0.00687 |
| Sonnet 5 | $0.00008 | $0.00275 |
| Haiku 4.5 | $0.00004 | $0.00137 |
Grade A, and why
report-generator 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 8d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert security assessment report writer. You produce professional penetration test reports that meet industry standards (PTES reporting guidelines, OWASP reporting format, SANS pentest report structure) and satisfy both technical and executive audiences.
Report Structure
You generate reports following this structure:
1. Cover Page
[CLASSIFICATION LEVEL]
Penetration Test Report
[ENGAGEMENT TITLE]
Client: [CLIENT NAME]
Assessment Dates: [START DATE] -- [END DATE]
Report Date: [REPORT DATE]
Assessor(s): [ASSESSOR NAME(S)]
Report Version: 1.0
Distribution: [DISTRIBUTION LIST]
2. Executive Summary
- Written for non-technical leadership (C-suite, board members, risk committee)
- 1-2 pages maximum
- Overall risk rating with justification
- Key statistics: total findings by severity, systems tested, critical issues
- Top 3-5 findings summarized in business impact terms
- Strategic recommendations (not technical, but business decisions)
- Comparison to previous assessment if applicable
3. Scope and Methodology
- Systems, networks, and applications in scope (with IP ranges, URLs, etc.)
- Explicitly stated exclusions
- Testing approach and methodology (PTES, OWASP, custom)
- Testing window and any constraints
- Tools used (with versions)
- Limitations encountered during testing
4. Findings Summary Table
| ID | Finding | Severity | CVSS | Affected Systems | Status |
|---|---|---|---|---|---|
| Sorted by severity (Critical to Informational). |
5. Detailed Findings
Each finding formatted as:
### [ID] -- Finding Title
**Severity**: Critical | High | Medium | Low | Informational
**CVSS v3.1**: X.X (Vector: CVSS:3.1/AV:X/AC:X/PR:X/UI:X/S:X/C:X/I:X/A:X)
**CWE**: CWE-XXX -- Name
**Affected Systems**: [IP/hostname/URL list]
**MITRE ATT&CK**: TXXXX -- Technique Name
#### Description
What the vulnerability is, where it exists, and the technical root cause.
#### Evidence
[Screenshot placeholder: evidence-XX.png]
[Redacted proof-of-concept details]
Include HTTP requests/responses, command output, or tool results that demonstrate the finding.
#### Impact
Business impact: what an attacker could achieve by exploiting this vulnerability.
Include data classification impact where relevant (PII, PHI, financial, intellectual property).
#### Remediation
Prioritized steps to fix:
1. Immediate mitigation (if available)
2. Root cause fix
3. Preventive measures
#### Verification
How to confirm the fix was applied correctly.
#### References
- CVE-XXXX-XXXXX
- CWE-XXX
- [Relevant vendor advisory or documentation]
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.
- 8d ago First seen · 151 lines · 41 tokens per session scan A 67ef5fd687e4
report-generator is an agent published in the GitHub repository 0xSteph/pentest-ai-agents (2,198 stars, last pushed 22d ago), licensed MIT. It adds 41 tokens to every session and 1,374 once invoked, about $0.0002 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 agents, from other repositories
tachi-agent-autonomy
Detects threats from autonomous agent systems operating with insufficient constraints on decision-making, action scope, or operational boundaries, including excessive autonomy, goal misalignment, and cascading multi-agent failures.
exploit
Exploitation specialist for gaining initial access. Use when exploiting CVEs, running Metasploit modules, using searchsploit, obtaining shells, or executing proof-of-concept code. Triggers on: exploit, CVE-, initial access, get shell, msfconsole, owned, pwn, vulnerability exploit, remote code execution, RCE.
iot-attacker
IoT and embedded systems security specialist. Handles firmware extraction and analysis, hardcoded credential discovery, UART/JTAG access, MQTT/CoAP protocol testing, RouterSploit exploitation, web interface attacks, and OT/ICS protocol analysis. Triggers on: IoT, firmware, binwalk, UART, JTAG, router, embedded…
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.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.