PentestGPT is an AI-driven framework for penetration testing and capture-the-flag challenges. It guides staged workflows such as reconnaissance, asset discovery, vulnerability identification, exploitation, and reporting, using large language models to operate tools and reason about findings. The catalogue includes skills and instructions for using it.
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.
npx agentmods add skills/greydgl/pentestgpt/improve-codebase-architecturenpx skills add GreyDGL/PentestGPT --skill improve-codebase-architecturegit clone --depth 1 https://github.com/GreyDGL/PentestGPTWrote 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.
[](https://agentmods.dev/skills/greydgl/pentestgpt/improve-codebase-architecture)<a href="https://agentmods.dev/skills/greydgl/pentestgpt/improve-codebase-architecture"><img src="https://agentmods.dev/badge/skills/greydgl/pentestgpt/improve-codebase-architecture.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00032 | $0.01203 |
| Opus 5 | $0.00016 | $0.00602 |
| Sonnet 5 | $0.00006 | $0.00241 |
| Haiku 4.5 | $0.00003 | $0.00120 |
Grade A, and why
improve-codebase-architecture 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 5d 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.
This is a copy
83% identical to improve-codebase-architecture — 41 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve Codebase Architecture
Surface architectural friction and propose deepening opportunities — refactors that turn shallow modules into deep ones. The aim is testability and AI-navigability.
This command is informed by the project's domain model and built on a shared design vocabulary:
- Run the
/codebase-designskill for the architecture vocabulary (module, interface, depth, seam, adapter, leverage, locality) and its principles (the deletion test, "the interface is the test surface", "one adapter = hypothetical seam, two = real"). Use these terms exactly in every suggestion — don't drift into "component," "service," "API," or "boundary." - The domain language in
CONTEXT.mdgives names to good seams; ADRs indocs/adr/record decisions this command should not re-litigate.
Process
1. Explore
Read the project's domain glossary (CONTEXT.md) and any ADRs in the area you're touching first.
Then use the Agent tool with subagent_type=Explore to walk the codebase. Don't follow rigid heuristics — explore organically and note where you experience friction:
- Where does understanding one concept require bouncing between many small modules?
- Where are modules shallow — interface nearly as complex as the implementation?
- Where have pure functions been extracted just for testability, but the real bugs hide in how they're called (no locality)?
- Where do tightly-coupled modules leak across their seams?
- Which parts of the codebase are untested, or hard to test through their current interface?
Apply the deletion test to anything you suspect is shallow: would deleting it concentrate complexity, or just move it? A "yes, concentrates" is the signal you want.
2. Present candidates as an HTML report
Write a self-contained HTML file to the OS temp directory so nothing lands in the repo. Resolve the temp dir from $TMPDIR, falling back to /tmp (or %TEMP% on Windows), and write to <tmpdir>/architecture-review-<timestamp>.html so each run gets a fresh file. Open it for the user — xdg-open <path> on Linux, open <path> on macOS, start <path> on Windows — and tell them the absolute path.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 67 lines · 32 tokens per session scan A 0026900866ed
improve-codebase-architecture is a skill published in the GitHub repository GreyDGL/PentestGPT (15,209 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 1,203 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 83% identical to improve-codebase-architecture, differing in 41 lines, and is treated as a copy.
Other skills, from other repositories
ml-engineering
Field-tested methodology and concrete recipes for training and operating large-scale LLM/VLM/multi-modal models end to end - choosing and benchmarking accelerators, storage and network; SLURM/Kubernetes orchestration; maximizing training throughput and fitting models in memory; diagnosing and surviving training…
seed-test-data
Seed reproducible local Langfuse data in ClickHouse and Postgres. Use for complex traces, long sessions, v3/v4 events, bulk list data, or frontend rendering and performance tests; never use ad hoc scripts or raw inserts.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
turborepo
Configure and troubleshoot Turborepo monorepos. Use for turbo.json, task pipelines, dependsOn, caching, filters, affected packages, CI optimization, environment variables, package boundaries, or shared internal packages.
infra-scaling
Tune and review Langfuse autoscaling for web, web-iso, and web-ingestion. Use for Terraform scale settings, RPM targets, scaling bounds, task counts, cost/performance tradeoffs, or Datadog evidence in the infrastructure repo.
clickhouse-best-practices
MUST USE when reviewing ClickHouse schemas, queries, or configurations. Contains 28 rules that MUST be checked before providing recommendations. Always read relevant rule files and cite specific rules in responses.