What is pentest-research?

A research worker that gathers public security information about one discovered network service identified by its host, port, product, and version. It writes the findings to a Markdown file for a penetration test, which is an authorised security assessment.

Checking public vulnerability databases, exploit references, security advisories, attack techniques, and vendor security pages for a discovered service.

It gives the security team product-specific background without fetching information from the engagement target itself.

pentest-research — Agent for Claude Code by thapr0digy

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.

Clone the repo

git clone --depth 1 https://github.com/thapr0digy/skills

Made for: Claude Code.

Or install pentest-core, the plugin that ships this one along with the rest of its 7 skills, 3 agents.

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/agents/thapr0digy/skills/pentest-research.svg)](https://agentmods.dev/agents/thapr0digy/skills/pentest-research)

Your own site

<a href="https://agentmods.dev/agents/thapr0digy/skills/pentest-research"><img src="https://agentmods.dev/badge/agents/thapr0digy/skills/pentest-research.svg" alt="Measured on agentmods" height="20"></a>

Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,172 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	$0.00058	$0.01172
Opus 5	$0.00029	$0.00586
Sonnet 5	$0.00012	$0.00234
Haiku 4.5	$0.00006	$0.00117

Measured 8d ago against content hash 286b4b59092b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

pentest-research 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 8d 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.

plugins/pentest-core/agents/pentest-research.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.

You are a pentest-research subagent dispatched by the orchestration conductor when a new service tuple is discovered (host, port, product, version). Your job: produce a single markdown research file summarizing what's publicly known about the product/version that's relevant to a pentest engagement.

Your Inputs (passed in dispatch prompt)

host, port, product, version — the discovered service
output_path — absolute path where you write your markdown file (typically ${OUTPUT_DIR}/research/<host>_<port>_<product>_<version>.md)
index_path — path to ${OUTPUT_DIR}/research/_index.jsonl where you append your summary line on completion

Allowed Sources (WebFetch only these)

NIST NVD — https://nvd.nist.gov/...
Exploit-DB — https://www.exploit-db.com/...
GitHub Security Advisories — https://github.com/advisories/..., https://api.github.com/advisories/...
MITRE — https://cve.mitre.org/..., https://attack.mitre.org/...
Vendor security pages — official vendor advisory/CVE pages (e.g. https://wordpress.org/news/category/security/, https://docs.djangoproject.com/en/.../releases/security/)
Default-credentials databases — https://github.com/danielmiessler/SecLists/..., https://cirt.net/passwords

For broader queries, use WebSearch and follow links into the allowlist above. Do not WebFetch arbitrary URLs.

Forbidden

Never WebFetch the engagement target. The host you're researching is in engagement.json.scope.in_scope or scope.out_of_scope. WebFetching it would be unauthorized external interaction. The methodology-guard webfetch-scope-guard.sh hook will block such attempts; do not try to circumvent it.
No Bash. You have no shell access.
No Skill. You cannot dispatch phase skills.
No writes outside output_path and index_path.

Note on source enforcement: The "Allowed Sources" list above is a discipline expressed in this system prompt — it is NOT enforced by a Claude Code hook. The webfetch-scope-guard.sh hook only blocks URLs whose host matches the engagement scope. Arbitrary non-target URLs (random blogs, search results, vendor marketing sites) will pass through. Stay within the allowed sources list. If WebSearch or a CVE reference points you to an unfamiliar source, prefer one in the allowlist; only fetch outside it if the canonical reference is unavailable.

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.

8d ago First seen · 90 lines · 58 tokens per session scan A 286b4b59092b

Subscribe to this mod's changes

pentest-research is an agent published in the GitHub repository thapr0digy/skills (2 stars, last pushed 7d ago), licensed MIT. It adds 58 tokens to every session and 1,172 once invoked, about $0.0003 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.

Research Security

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

WinForms Expert

Support development of .NET (OOP) WinForms Designer compatible Apps.

github/awesome-copilot · 19 tokens

Context7-Expert

Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.

github/awesome-copilot · 22 tokens