A security-review mapping skill that inventories the repositories making up a target, determines their technology stacks from the code, and maps security-relevant areas such as authentication, cryptography, inputs, secrets, and trust boundaries.

Use it at the start of the code-review stage when repository access is available, before /pt-code-plan, to create code/review-map.md. Skip it for black-box reviews where the code cannot be accessed.

It gives later security analysis a stable picture of which code exists, what it is built with, and where important risks may live. This focuses the review instead of relying on a broad, unfocused scan.

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-code-map/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-code-map/github.svg)](https://agentmods.dev/skills/brovar/10x-pentest/pt-code-map)

Your own site

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

Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,669 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	$0.00142	$0.01669
Opus 5.5	$0.00057	$0.00668
Sonnet 5.5	$0.00028	$0.00334
Haiku 4.5	$0.00014	$0.00167

Measured 1mo ago against content hash eaf78834a9fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pt-code-map 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 1mo 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-code-map/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/pt-code-map — Repo Inventory, Stack & Code Map (Stage 3)

Open the code stage by (1) enumerating the repositories the target is built from as a stable R-NNN registry, (2) authoritatively determining each repo's technology stack from the code — the input that drives methodology selection in /pt-code-plan — and (3) building the security-focused code map: where auth, crypto, input handling, sinks/sources, secrets, and each code-routed objective live, plus the cross-repo trust boundaries. Writes code/review-map.md (shape: foundation/artifact-templates.md). The repo+stack+targeting layer that turns code review from a blind sweep into a systematic, stack-aware pass. Analog of 10x-research, scoped to security.

When to use, when to skip

Use when the engagement has repo access (~90% of cases) — it opens the code stage.
Skip the entire code stage (this + /pt-code-plan + /pt-code-scan + /pt-code-review) when the engagement is black-box / repo_access: false — go straight to /pt-dynamic-plan.

Initial Response

With <engagement-id>: proceed to Step 0.
Without: print Usage: /pt-code-map <engagement-id>. and STOP.

Inputs

test-objectives.md — [blocking] (the code- and both-routed objectives to target).
target-profile.md — [blocking] (classes + recon-level stack to reconcile against).
scope.md — [blocking] (readiness ≠ blocked; confirms repo_access: true; the in-scope repo assets).
Source repositories (one or many) — [blocking for this stage].

Process

Step 0: Validate + resume

Validate scope.md (repo_access: true, else STOP → the code stage doesn't apply, go /pt-dynamic-plan) and test-objectives.md (creation gate passed). Resume: if code/review-map.md exists, amend it append-only — new repos get new R-NNN, new code anchors are added; never renumber a repo or rewrite prior anchors.

Step 1: Repo inventory + authoritative per-repo stack

Enumerate every in-scope repository as R-NNN: role/service, maps_to the deployed asset it builds (A-NNN), primary language. For each repo, determine the stack from the code (not OSINT): languages, frameworks, build system, data stores, IaC (Terraform/K8s/CloudFormation), cloud SDKs, crypto/auth libraries — with versions where knowable (SCA/CVE). This is authoritative for Stage 3; reconcile with target-profile.md and, on a material divergence (a framework/service recon missed), flag it as a recon gap for the operator (a /pt-recon-review follow-up) — but never rewrite the locked target-profile.md.

Read the full file on GitHub · 112 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.

1mo ago First seen · 112 lines · 0 tokens per session scan A eaf78834a9fb

Subscribe to this mod's changes

pt-code-map is a skill published in the GitHub repository brovar/10x-pentest (3 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 142 tokens to every session and 1,669 once invoked, about $0.0006 per session on Opus 5.5. 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.

Code review Security

autoreview

Structured code review through the shared OpenClaw agent-skills installation.

openclaw/clawhub · 17 tokens

omh-code-review

This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).

rlaope/oh-my-hermes · 48 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens

re0-merge

Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…

LilMGenius/paperthin · 70 tokens

explore-unknowns

Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…

dzhng/skills · 162 tokens

asplos-writing-style

Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…

brycewang-stanford/Awesome-Journal-Skills · 65 tokens

10x-pentest: Skill for Claude Code