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/HoangNguyen0403/agent-skills-standardWrote 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/commands/hoangnguyen0403/agent-skills-standard/pentest)<a href="https://agentmods.dev/commands/hoangnguyen0403/agent-skills-standard/pentest"><img src="https://agentmods.dev/badge/commands/hoangnguyen0403/agent-skills-standard/pentest/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/commands/hoangnguyen0403/agent-skills-standard/pentest"><img src="https://agentmods.dev/badge/commands/hoangnguyen0403/agent-skills-standard/pentest.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 | $0.00000 | $0.00653 |
| Opus 5 | $0.00000 | $0.00327 |
| Sonnet 5 | $0.00000 | $0.00131 |
| Haiku 4.5 | $0.00000 | $0.00065 |
Grade A, and why
pentest 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 9d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pentest
PTES-aligned adversarial security audit for backend, frontend, and mobile applications. Produces a CVSS-scored Hacker Report with verified PoCs and phased remediation.
Input: $ARGUMENTS
Optional args: slug=, ticket=<id/url>, mode=interactive|autonomous|channel, channel=, auto_continue=true|false, profile=business|hybrid|technical.
Instructions
Execute the following steps for $ARGUMENTS.
🕵️♂️ Penetration Test (PTES-Aligned)
Goal: Execute a red-team assessment across backend, frontend, and mobile targets with verified PoCs and audit-grade evidence.
Steps
-
Scope and authorization:
- Determine mode (
whitebox,greybox,blackbox) and targets. - Verify explicit authorization; stop if unauthorized.
- Determine mode (
-
Intel and threat model:
- Identify stack, endpoints, parameters, local storage, schemes, and secrets.
- Use
common-security-audit,common-dast-tooling, and architecture docs when available. - Map trust boundaries, secrets, external integrations, and privileged workflows before exploit attempts.
-
Vulnerability analysis:
- Run scans and delegate: SAST/SCA to
specialist-aspm-correlator, dynamic/logic tospecialist-logic-hacker, binary/mobile tospecialist-mobile-reverser. - Rank targets by
exposure × sensitivity × auth_coverage.
- Run scans and delegate: SAST/SCA to
-
Exploit verification:
- No Exploit = No Report. Discard unverified findings.
- Build reproducible PoCs and record preconditions, payloads, evidence, and blast radius.
-
Reporting:
- Write
artifacts/security-review.mdwith assumptions, source provenance, review context, runtime contract, PoCs, blast radius, finding confidence, exploit path, evidence gaps, and handoff notes. - Emit
artifacts/security-review.dev.md,artifacts/security-review.appsec.md, orartifacts/security-review.exec.mdonly when leadership, client, or AppSec reporting is in scope. - Score from 100: Critical -25 (cap 25), High -15 (cap 40), Medium -8, Low -3.
- Reuse the existing
security-review.mdrecord when pentest follows earlier design or PR security review work. - Deliver findings in the standard template below.
- Write
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.
- 9d ago First seen · 57 lines · 0 tokens per session scan A ec666dfadddd
pentest is a command published in the GitHub repository HoangNguyen0403/agent-skills-standard (565 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 653 tokens. 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 2026-09-03.
Other commands, from other repositories
ralph
Ralph - persistent self-referential execution loop wrapping ultrawork with a spawned independent judge.
tools
Manage MCP tools with natural language commands to list, enable, and disable tools and tool groups.
incident
An incident-response assistant for guiding work when a software service has a serious failure or disruption.
scan
A security scanning assistant command with guidance on its workflow, usage, and how an AI agent should behave during a scan.
page
Create Next.js page following mirror pattern.
checklist
Generate a custom checklist for the current feature based on user requirements.