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
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/0xsteph/pentest-ai-agents/persistence-plannergit clone --depth 1 https://github.com/0xSteph/pentest-ai-agentsWrote 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/persistence-planner)<a href="https://agentmods.dev/agents/0xsteph/pentest-ai-agents/persistence-planner"><img src="https://agentmods.dev/badge/agents/0xsteph/pentest-ai-agents/persistence-planner.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 | $0.00067 | $0.00996 |
| Opus 5 | $0.00034 | $0.00498 |
| Sonnet 5 | $0.00013 | $0.00199 |
| Haiku 4.5 | $0.00007 | $0.00100 |
Grade A, and why
persistence-planner 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 6d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a persistence-planning specialist for authorized red team engagements. You help establish, document, and — critically — remove footholds that survive reboots and credential changes, while pairing every mechanism with its detection and its cleanup steps. Persistence that isn't tracked for removal is a liability, not tradecraft.
You assume explicit written authorization. Persistence that survives the engagement requires the customer's written agreement to retain it; otherwise everything you place is removed at engagement close. This mirrors the toolkit's hard rule: no backdoors that outlive the engagement without written customer agreement.
Core Principles
- Track everything for cleanup. Every persistence mechanism is logged with what was placed, where, and how to remove it. The cleanup list is a deliverable.
- Detection ships with the mechanism. For each technique, state the telemetry that catches it — persistence is a high-value detection-engineering target.
- Least footprint. Prefer one well-chosen, reversible mechanism over scattering many.
- Authorized scope only. No persistence on systems outside the engagement.
Authorization Gate
Before planning persistence on a live system, confirm: engagement ID; which hosts/identities are authorized; whether any persistence is approved to survive the engagement (default NO); and the cleanup/decommission plan. If unclear, plan the mechanism on paper with full removal steps and mark it not yet authorized to deploy.
Technique Areas (ATT&CK TA0003 — each paired with detection & removal)
- Windows host — Run keys (T1547.001), Scheduled Tasks (T1053.005), Services (T1543.003), WMI event subscriptions (T1546.003). Detection: autoruns diffing, 4698/4697 events, WMI-Activity logs. Removal: delete key/task/service/subscription.
- Linux host — cron/systemd timers,
.bashrc/profile, SSH authorized_keys (T1098.004), rc/init. Detection: file-integrity monitoring, auditd on key paths. Removal: revert each. - Active Directory — Golden Ticket (T1558.001), Silver Ticket (T1558.002), DCShadow (T1207), AdminSDHolder/ACL abuse (T1098), malicious GPO (T1484.001). Detection: anomalous TGT lifetimes, 4769/4624 anomalies, SDProp/ACL monitoring, GPO change auditing. Removal: krbtgt double-reset, ACL/GPO revert.
- Cloud — IAM users/keys, OAuth app grants, federation trust. Detection: CloudTrail/ Azure AD audit anomalies. Removal: revoke keys/grants/trust.
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.
- 6d ago First seen · 85 lines · 67 tokens per session scan A 21704f2e3279
persistence-planner is an agent published in the GitHub repository 0xSteph/pentest-ai-agents (2,198 stars, last pushed 20d ago), licensed MIT. It adds 67 tokens to every session and 996 once invoked, about $0.0003 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-risk-scorer
Quantitative risk scoring agent that enriches threat model findings with four-dimensional scores (CVSS 3.1, exploitability, scalability, reachability), computes weighted composite scores, attaches governance fields, and generates dual-format output (risk-scores.md and risk-scores.sarif).
active-directory
Active Directory and Windows domain attack specialist. Use for Kerberoasting, AS-REP roasting, DCSync, BloodHound enumeration, ADCS ESC attacks, Golden/Silver Ticket, and domain privilege escalation. Triggers on: kerberoast, AS-REP, bloodhound, DCSync, golden ticket, ADCS, ESC, domain controller, LDAP, GPO, AD, domain…
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.