A setup step for opening a new penetration-testing engagement, meaning one complete authorised security test. It creates an engagement folder and an identity file, or starts a retest from an earlier engagement.

Use it to start a new test, create a retest from a previous one, or prepare the workspace before defining its scope.

It gives each security test a separate place for its scope, notes, and other working documents, while preventing accidental name collisions.

How brovar/10x-pentest configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to brovar/10x-pentest. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/brovar/10x-pentest/main/.github/skills/pt-new/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/brovar/10x-pentest

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/brovar/10x-pentest/pt-new/github.svg)](https://agentmods.dev/skills/brovar/10x-pentest/pt-new)

Your own site

<a href="https://agentmods.dev/skills/brovar/10x-pentest/pt-new"><img src="https://agentmods.dev/badge/skills/brovar/10x-pentest/pt-new/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/brovar/10x-pentest/pt-new"><img src="https://agentmods.dev/badge/skills/brovar/10x-pentest/pt-new.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,558 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00092	$0.01558
Opus 5	$0.00046	$0.00779
Sonnet 5	$0.00018	$0.00312
Haiku 4.5	$0.00009	$0.00156

Measured 9d ago against content hash 6c23a0fbddc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pt-new 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.

.github/skills/pt-new/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/pt-new — Open a New Engagement

Bootstrap a new engagement folder under context/engagements/<engagement-id>/. Creates the engagement.md identity file (per foundation/engagement-schema.md) and points the operator at /pt-scope. In retest mode (--from <prior-engagement-id>) it also seeds the prior engagement's artifacts forward as editable templates. An "engagement" is one security test end-to-end — every staged artifact lives inside its <engagement-id> folder.

When to use, when to skip

Use to start a new engagement, or a retest (--from) of a prior one.
Skip if the engagement folder already exists — this skill refuses collisions (that IS its re-run behavior); to continue an existing engagement, run the stage skill you left off at, or /pt-run to be routed.

Initial Response

With an argument: parse it and proceed to Validation.
Without: print the usage block and STOP:

I'll open a new engagement folder. Provide an engagement-id (kebab-case slug):

  /pt-new acme-web-q3
  /pt-new acme-web-q3 external web app + API, grey-box, repo access
  /pt-new acme-web-q3-retest --from acme-web-q3

The first token is the engagement-id. `--from <prior-id>` opens a retest seeded from a prior
engagement; anything else is freeform intent for the title. The id must be kebab-case and unique
across context/engagements/ and context/archive/.

Inputs

<engagement-id> argument — [blocking] (the id + optional freeform intent).
--from <prior-engagement-id> — [optional]; retest mode. The prior engagement folder is [blocking in retest mode] — it must exist in engagements/ or archive/.

Process

Argument parsing

First token = engagement-id (strip leading @, trailing /; if it contains /, take the last segment).
--from <prior-id> anywhere = retest mode.
Everything else = freeform intent for the title (not inserted verbatim).

Validation (any failure → STOP)

kebab-case: <id> matches ^[a-z][a-z0-9]*(-[a-z0-9]+)*$, else error: engagement-id "<id>" is not kebab-case.
Uniqueness: neither context/engagements/<id>/ nor context/archive/<id>/ exists, else error: engagement "<id>" already exists.
Parent exists: context/engagements/ present, else error: run /pt-init first.
Retest only: --from parent exists, else error: --from parent "<prior-id>" not found.

Read the full file on GitHub · 117 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.

9d ago First seen · 117 lines · 0 tokens per session scan A 6c23a0fbddc3

Subscribe to this mod's changes

pt-new is a skill published in the GitHub repository brovar/10x-pentest (3 stars, last pushed 27d ago), licensed Apache-2.0. It adds 92 tokens to every session and 1,558 once invoked, about $0.0005 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 2026-08-31.

Security

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

10x-pentest: Skill for Claude Code