p6-pentest

p6-pentest is a command for Claude Code from jonase47/ccpr. It costs 0 tokens per session (899 once invoked), scanned A, original, MIT.

A coordinated penetration test that simulates attacks against an application through separate phases. A penetration test is an authorized security assessment that looks for weaknesses by using controlled attack attempts.

In plain words
What is it for?
Use it to assess the attack surface, authentication, permissions, input handling, and business-critical flows of your own deployed or local system.
Why use it?
It combines reconnaissance, login and session checks, access-control tests, injection tests, and business-logic tests into one security review.

Command for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths.

Install

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.

agentmods
npx agentmods add commands/jonase47/ccpr/p6-pentest
Clone the repo
git clone --depth 1 https://github.com/jonase47/ccpr

Made for: Claude Code.

Wrote 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.

agentmods badge for p6-pentest

README.md
[![agentmods](https://agentmods.dev/badge/commands/jonase47/ccpr/p6-pentest.svg)](https://agentmods.dev/commands/jonase47/ccpr/p6-pentest)
Your own site
<a href="https://agentmods.dev/commands/jonase47/ccpr/p6-pentest"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p6-pentest.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 899 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00899
Opus 5 $0.00000 $0.00449
Sonnet 5 $0.00000 $0.00180
Haiku 4.5 $0.00000 $0.00090

Measured 2d ago against content hash 17094f910084, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

p6-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 2d 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.

commands/p6-pentest.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/p6-pentest – Penetration Test

Conducts an active attack simulation. Each attack phase is a separate sub-skill.

Argument: $ARGUMENTS = [attack vector/area]

If provided: Focus the pentest on the specified vector. If not provided: Run all phases.

Flow

0. Ensure Sub-Index Exists

Make sure docs/quality/PENTEST.md exists as a sub-index with the standard header (Status / Last Updated / Key Decisions / Open Risks / Detail Files / Gate Notes — see ~/.claude/docs/PROJECT_PHASES.md). If missing, create it with empty placeholders. The five p6-pentest-* sub-skills below each refresh their own row in this sub-index's Detail Files table.

1. Reconnaissance

/p6-pentest-recon $ARGUMENTS – Gather information, map the attack surface.

2. Auth & Session Attacks

/p6-pentest-auth $ARGUMENTS – Test brute-force, tokens, JWT confusion.

3. Authorisation & Access Control

/p6-pentest-authz $ARGUMENTS – Test IDOR, privilege escalation.

4. Injection Attacks

/p6-pentest-injection $ARGUMENTS – Test SQLi, XSS, command injection.

5. Business Logic Attacks

/p6-pentest-logic $ARGUMENTS – Test value manipulation, race conditions.

6. Roll Up Sub-Index to Phase Index

After all p6-pentest-* sub-skills have run, summarise the PENTEST sub-index into the phase index docs/quality/QA.md:

  • Add an entry in the phase-index Detail Files table for [PENTEST.md](PENTEST.md) (the sub-index itself), status complete once all five sub-skill rows are complete (or needs-rework).
  • Lift any successful exploit (auth bypass, IDOR, RCE, injection, logic abuse) into the phase-index Open Risks as Critical.

Notes

  • Maintain order: Recon informs all subsequent phases
  • Phases 2–5 can partially run in parallel after Recon
  • For missing features (e.g. no auth): skip phase by setting its detail file frontmatter status: active and a body note "N/A — out of scope"
  • Detail files: pentest_recon.md, pentest_auth.md, pentest_authz.md, pentest_injection.md, pentest_logic.md under the PENTEST.md sub-index
  • Only against own system, PoCs non-destructive

Read the full file on GitHub · 64 lines

Changes

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.

  1. 2d ago First seen · 64 lines · 0 tokens per session scan A 17094f910084

Subscribe to this mod's changes

p6-pentest is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 899 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.