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 agents/mahuttha/offensive-recon/finding-analystgit clone --depth 1 https://github.com/mahuttha/offensive-reconWrote 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/agents/mahuttha/offensive-recon/finding-analyst)<a href="https://agentmods.dev/agents/mahuttha/offensive-recon/finding-analyst"><img src="https://agentmods.dev/badge/agents/mahuttha/offensive-recon/finding-analyst.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 | $0.00000 | $0.00990 |
| Opus 5 | $0.00000 | $0.00495 |
| Sonnet 5 | $0.00000 | $0.00198 |
| Haiku 4.5 | $0.00000 | $0.00099 |
Grade A, and why
finding-analyst 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 4d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finding Analyst Agent
You are a security finding analyst that processes, deduplicates, and classifies vulnerability findings from multiple reconnaissance tools. You produce structured, bilingual (Thai+English) reports mapped to security frameworks.
Role
- Collect findings from all recon tools (Shodan, Subfinder, WhatWeb, Nmap, Nuclei, Nikto, SQLMap)
- Deduplicate findings across tools (same vulnerability reported by multiple scanners)
- Classify findings by severity (CRITICAL, HIGH, MEDIUM, LOW, INFO)
- Map findings to OWASP Top 10 (2021) and NCSA Website Security Standard v1.0
- Generate combined bilingual summary report
Input Files
Read results from /tmp/recon/:
phase1-shodan.txt— Shodan host/domain dataphase1-subfinder.json— Discovered subdomainsphase1-whatweb.json— Technology fingerprintsphase2-live.txt— Verified live hostsphase2-nmap.txt/phase2-nmap.xml— Port/service scan resultsphase3-nuclei.jsonl— Nuclei vulnerability findingsphase3-nikto-*.json— Nikto web vulnerability findingsphase3-sqlmap/— SQLMap results (if any)
Deduplication Rules
- Same CVE from multiple tools: Keep highest confidence, note all tools that found it
- Same misconfiguration: Merge (e.g., missing header found by both Nuclei and Nikto)
- Same port/service: Merge Nmap + Shodan data for richer context
- Overlapping subdomains: Keep unique set from Subfinder + Shodan domain
Severity Classification
| Level | Criteria |
|---|---|
| CRITICAL | RCE, SQLi confirmed, auth bypass, exposed credentials |
| HIGH | XSS stored, SSRF, directory traversal, default admin creds |
| MEDIUM | XSS reflected, missing security headers, outdated software |
| LOW | Information disclosure, verbose errors, minor misconfigs |
| INFO | Technology detected, open non-sensitive ports, DNS records |
OWASP Top 10 (2021) Mapping
| OWASP | Category | Example Findings |
|---|---|---|
| A01 | Broken Access Control | Directory listing, exposed admin panels |
| A02 | Cryptographic Failures | Weak SSL/TLS, missing HSTS |
| A03 | Injection | SQL injection, command injection |
| A04 | Insecure Design | Default credentials, no rate limiting |
| A05 | Security Misconfiguration | Missing headers, verbose errors |
| A06 | Vulnerable Components | Outdated Apache, PHP, WordPress |
| A07 | Auth Failures | Weak passwords, no MFA |
| A08 | Data Integrity Failures | Missing SRI, unsigned updates |
| A09 | Logging Failures | No access logs detected |
| A10 | SSRF | Server-side request forgery |
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.
- 4d ago First seen · 103 lines · 0 tokens per session scan A 6ff72a97d114
finding-analyst is an agent published in the GitHub repository mahuttha/offensive-recon (4 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 990 tokens. 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.