p6-pentest-logic

p6-pentest-logic is a command for Claude Code from jonase47/ccpr. It costs 0 tokens per session (807 once invoked), scanned A, original, MIT.

A security test that tries to manipulate an application's business rules, such as prices, quantities, bookings, or workflow steps. It checks for race conditions, which happen when simultaneous actions produce an incorrect result, and ways to bypass required steps.

In plain words
What is it for?
Use it to test payment calculations, booking flows, order quantities, and other business-critical processes with safe attack attempts.
Why use it?
It finds flaws that can let users change values, repeat actions, or skip rules even when the application otherwise appears to work correctly.

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-logic
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-logic

README.md
[![agentmods](https://agentmods.dev/badge/commands/jonase47/ccpr/p6-pentest-logic.svg)](https://agentmods.dev/commands/jonase47/ccpr/p6-pentest-logic)
Your own site
<a href="https://agentmods.dev/commands/jonase47/ccpr/p6-pentest-logic"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p6-pentest-logic.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 807 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 $0.00807
Opus 5 $0.00000 $0.00404
Sonnet 5 $0.00000 $0.00161
Haiku 4.5 $0.00000 $0.00081

Measured 2d ago against content hash 5eda5f0acb35, 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-logic 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-logic.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/p6-pentest-logic – Business Logic Attacks

Tests manipulation of business logic: prices, quantities, race conditions, flow bypasses.

Argument: $ARGUMENTS = [business area/feature]

If provided: Focus on the specified area. If not provided: Test all business-critical flows.

Prerequisites

  • /p6-pentest-injection completed
  • Business logic implemented

Agent

  • Type: pentester
  • Model: sonnet

Context (Orchestrator prepares)

Orchestrator reads in advance and delivers inline:

  • From src/: Business logic code (price calculation, booking, workflows)
  • From FEATURES.md/BACKLOG.md: Business rules and expected behaviour

Prompt Template

Goal: Test business logic for manipulation in: [area]

Business Logic Code: [inline from src/]

Business Rules: [inline from FEATURES.md]

Output Format: Table with max. 10 attack attempts:

# Attack Method Result Severity PoC

Types: Value Manipulation, Race Condition, Flow Bypass, Double Execution

Constraints:

  • Business logic attacks ONLY – no injection, no auth
  • PoC minimal and non-destructive
  • For simple apps without business logic: "N/A" is sufficient

Orchestrator Checkpoint

  • Critical business processes tested?
  • Race conditions checked?

Write Detail File

Write the result to docs/quality/pentest_logic.md (overwrite). Frontmatter:

---
phase: P6
subskill: pentest-logic
status: active
last_updated: <DD.MM.YYYY>
---

Body sections: ## Scope, ## Findings (business-logic abuse table with PoCs), ## Severity Summary.

Update Sub-Index

Update docs/quality/PENTEST.md:

  • Set **Last Updated:** <DD.MM.YYYY>.
  • In its Detail Files table: ensure a row for [pentest_logic.md](pentest_logic.md) with status complete.
  • Lift any logic-abuse finding into Open Risks with severity.

Handover Epilogue

Before writing. docs/HANDOVER.md is capped — the file states its own limit in its header (default: ≤5 KB / ~150 lines). Two rules follow from that, and neither is optional:

  • Replace this command's previous epilogue block, do not append a second one. Stacking is what pushes the file over; one skill run has been measured adding 1021 B, ~20 % of the cap.
  • If the file is already near its cap, shorten before you add. Reading the cap sentence is not the same as measuring: check the actual size, and when there is no room, condense existing content or hand the user /cleanup instead of growing the file further.

Read the full file on GitHub · 90 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 · 90 lines · 0 tokens per session scan A 5eda5f0acb35

Subscribe to this mod's changes

p6-pentest-logic 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 807 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.