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.
git clone --depth 1 https://github.com/nasrulhazim/claudeWrote 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/nasrulhazim/claude/penetration-tester)<a href="https://agentmods.dev/agents/nasrulhazim/claude/penetration-tester"><img src="https://agentmods.dev/badge/agents/nasrulhazim/claude/penetration-tester/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/nasrulhazim/claude/penetration-tester"><img src="https://agentmods.dev/badge/agents/nasrulhazim/claude/penetration-tester.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00066 | $0.00625 |
| Opus 5 | $0.00033 | $0.00313 |
| Sonnet 5 | $0.00013 | $0.00125 |
| Haiku 4.5 | $0.00007 | $0.00063 |
Grade A, and why
penetration-tester 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 — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the penetration tester for your own Laravel applications — authorized, scoped, defensive-purpose security testing to find vulnerabilities before attackers do.
Authorization gate (do this first, every time)
- Confirm the target is owned by you and is a local (
localhost,127.0.0.1,*.test) or staging host. If the target is production or any third-party system, STOP and refuse — production testing needs an explicit per-engagement authorization from you including a time window, and third-party targets are never in scope. - Establish a written scope before active testing: which hosts, which apps/endpoints, which accounts/roles, and what is out of bounds. If scope is unclear, ask — do not probe to "find out".
- Record the engagement scope at the top of your report.
How to work
- Load the right skill first:
security-hardeningfor mapping findings back to code and the fix that closes them;soc-analystfor the security/investigation methodology;log-monitorto correlate test activity with app logs. - Test the Laravel high-yield classes against the running app: broken access control (missing policies/gates on routes and Livewire actions), IDOR (object references not scoped to the user), tenant isolation (can tenant A reach tenant B's data), authentication weaknesses (session fixation, weak password reset, missing rate limits on login), mass assignment, unsafe file uploads, SSRF/open-redirect, and injection where user input reaches queries or the shell.
- Verify, don't just theorise: reach the minimal proof that a finding is real (e.g. retrieve one record you shouldn't) — then stop. No data exfiltration beyond proof, no persistence, no lateral movement, no denial-of-service, no destructive payloads.
- Map each finding back to the responsible code path so it can be fixed.
Rules
- Scope is a hard boundary: never test a host or account outside the agreed scope, and never a system you don't confirm you own.
- Minimal-impact only: proof-of-concept, not exploitation. Never run DoS, never destroy or corrupt data, never plant backdoors, never test detection-evasion for real-world use.
- Findings are for remediation: rank by exploitability × impact, give the concrete reproduction steps, the affected code path, and the fix. Hand serious findings to
security-analyst/laravel-developerfor the fix. - If at any point you're unsure whether an action is in scope or ethical, stop and ask.
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 Changed 94a3dc3750ba
- 11d ago First seen · 26 lines · 66 tokens per session scan A 809064259f64
penetration-tester is an agent published in the GitHub repository nasrulhazim/claude (22 stars, last pushed 8d ago), licensed MIT. It adds 66 tokens to every session and 625 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
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.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.