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 skills add crazyMarky/pentest-skills --skill recon-dir-scangit clone --depth 1 https://github.com/crazyMarky/pentest-skillsWrote 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/crazymarky/pentest-skills/recon-dir-scan)<a href="https://agentmods.dev/skills/crazymarky/pentest-skills/recon-dir-scan"><img src="https://agentmods.dev/badge/skills/crazymarky/pentest-skills/recon-dir-scan/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.
<a href="https://agentmods.dev/skills/crazymarky/pentest-skills/recon-dir-scan"><img src="https://agentmods.dev/badge/skills/crazymarky/pentest-skills/recon-dir-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 148 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 149 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00052 | $0.02900 |
| Opus 5 | $0.00026 | $0.01450 |
| Sonnet 5 | $0.00010 | $0.00580 |
| Haiku 4.5 | $0.00005 | $0.00290 |
Grade A, and why
recon-dir-scan 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 434 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Directory and File Enumeration
Authorization Warning
IMPORTANT: Directory scanning without proper authorization may be detected as intrusion attempts. Always ensure you have:
- Written permission from the target application owner
- Defined scope of authorized testing
- Legal compliance with local regulations
Prerequisites
Required tools that must be installed on your system:
- ffuf -
go install github.com/ffuf/ffuf@latest - gobuster -
go install github.com/OJ/gobuster/v3/cmd/gobusterdir@main
Optional tools:
- feroxbuster -
cargo install feroxbuster - dirsearch -
pip install dirsearch - dirb - Package manager installation
Quick Start
Most commonly used commands for directory enumeration:
Fast Directory Scan (ffuf)
ffuf -w wordlist.txt -u https://target.com/FUZZ
Recursive Scan with Status Codes
ffuf -w wordlist.txt -u https://target.com/FUZZ -mc 200,301,302 -recursion
Gobuster Quick Scan
gobuster dir -u https://target.com -w wordlist.txt -t 50
Common Scenarios
Scenario 1: Basic Directory Fuzzing
When you need to discover directories and files:
ffuf -w wordlist.txt -u https://target.com/FUZZ
Parameters:
-w wordlist.txt- Wordlist path-u- Target URL with FUZZ keyword-t- Threads (default: 40)
Example:
ffuf -w /usr/share/seclists/Discovery/Web-Content/common.txt -u https://target.com/FUZZ
Scenario 2: Filter by Status Code
When you only want specific HTTP status codes:
ffuf -w wordlist.txt -u https://target.com/FUZZ -mc 200,301,302,403
Status Code Filters:
| Code | Meaning |
|---|---|
| 200 | OK (valid page) |
| 301,302 | Redirects |
| 403 | Forbidden (directory exists, no access) |
| 401 | Authentication required |
Negation filter (exclude codes):
ffuf -w wordlist.txt -u https://target.com/FUZZ -mc 200,204,301,302,307,401,403 -mc 404
Scenario 3: Recursive Scanning
What ships with it
11 files 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.
- assets/api-endpoints.txt 3.4 KB
- assets/common-dirs.txt 5.2 KB
- assets/common-files.txt 5.2 KB
- assets/hidden-files.txt 2.5 KB
- references/ffuf_guide.md 3.8 KB
- references/gobuster_guide.md 3.3 KB
- references/wordlist_guide.md 4.3 KB
- scripts/dir_scan_storage.py 2.4 KB runs code
- scripts/ffuf_results_parser.py 4.9 KB runs code
- scripts/merge_wordlists.py 2.4 KB runs code
- scripts/status_code_analyzer.py 5.3 KB runs code
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.
- 10d ago First seen · 434 lines · 52 tokens per session scan A 27868235e91c
recon-dir-scan is a skill published in the GitHub repository crazyMarky/pentest-skills (307 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 52 tokens to every session and 2,900 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 2026-08-30.
Other skills, from other repositories
incident-response-fileanalyser
Static malware reverse-engineering and threat-intelligence triage for unknown files, Windows EXE/PE binaries, scripts, archives, ISOs, JavaScript, PowerShell, documents, and unpacked payloads. Use when a user provides a sample path, hash, filename, or file and asks whether it is malicious, benign, suspicious, contains…
pentest-cve-vulnerability-research-helper
CVE and vulnerability research skill for exact CVE lookup, product/version applicability, exploit maturity, KEV/PoC status, source ranking, contradiction handling, and non-destructive validation guidance.
pentest-web-enumeration
Authorized web enumeration for one or many websites or web applications, including live-target normalization, HTTP and TLS fingerprinting, technology and platform identification, virtual-host discovery, crawling, JavaScript and API endpoint extraction, focused directory and sensitive-file discovery, CMS-specific…
web-pentest-skill
Analyze supplied artifacts from authorized web assessments with bounded defensive reasoning, evidence review, resumable workflow planning, and static reporting. Use for offline artifact analysis and explicitly reviewed task planning; never for autonomous exploitation, unreviewed target scanning, or executing…
pentest-hacktricks-finder
Support skill for HackTricks technique research, payload ideas, bypasses, prerequisites, caveats, and edge-case behavior across web, network, cloud, and application security topics. Use as owner only when research is the current blocker.
incident-response-bec
BEC and AiTM incident-response skill for suspicious sign-ins, mailbox abuse, forwarding, inbox rules, session theft, token replay, consent abuse, and secondary phishing.