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.

pt-code-map — Skill by brovar

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 skills/brovar/10x-pentest/pt-code-map

Any agent

npx skills add brovar/10x-pentest --skill pt-code-map

Clone the repo

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

Made for: Claude Code, Codex.

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. 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.

Model	Per session	Once invoked
Fable 5	$0.00142	$0.01669
Opus 5	$0.00071	$0.00834
Sonnet 5	$0.00028	$0.00334
Haiku 4.5	$0.00014	$0.00167

Measured 2d ago against content hash eaf78834a9fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

.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.

2d 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 (2 stars, last pushed 20d ago), licensed Apache-2.0. It adds 142 tokens to every session and 1,669 once invoked, about $0.0007 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.

Code review Planning Security

systematic-debugging

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

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens