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 commands/ogrodev/fsociety/recongit clone --depth 1 https://github.com/ogrodev/fsocietyWhat 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 | $0.00017 | $0.00530 |
| Opus 5 | $0.00009 | $0.00265 |
| Sonnet 5 | $0.00003 | $0.00106 |
| Haiku 4.5 | $0.00002 | $0.00053 |
Grade A, and why
recon 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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Storage Policy: ALL output files MUST be saved in the project directory. NEVER write to
/tmp/or any system temporary directory.
Reconnaissance Workflow
Target: $ARGUMENTS
Execute a comprehensive reconnaissance workflow against the target using Hexstrike MCP tools. Follow this sequence:
Step 1: Load Tools
Use ToolSearch to load these Hexstrike tools:
subfinder_scan— passive subdomain enumerationhttpx_probe— HTTP probing and tech detectionwafw00f_scan— WAF detection and fingerprintingdetect_technologies_ai— AI-powered technology identificationkatana_crawl— web crawling for endpoint discoverygau_discovery— historical URL discovery from archivesnmap_scan— port scanning for initial service identification
Step 2: Subdomain Enumeration
Run subfinder_scan against the target domain to discover subdomains. Then probe discovered subdomains with httpx_probe to identify live hosts and their technologies.
Step 3: WAF Detection
Run wafw00f_scan on each live subdomain to identify WAF/CDN protection. This is critical for later attack planning — tools and payloads must be selected based on WAF type.
Step 4: Technology Detection
Run detect_technologies_ai on the main target and key subdomains. This identifies the full tech stack (CMS, frameworks, languages, servers) and recommends testing approaches.
Step 5: Port Scanning
Run nmap_scan against the target for a standard port scan to identify open services beyond HTTP/HTTPS.
Step 6: Crawling & URL Discovery
Run katana_crawl on the main target for deep crawling with JavaScript rendering. Also run gau_discovery to find historical URLs from web archives that may reveal hidden endpoints.
Step 7: Save Results
Save a structured reconnaissance summary to the project directory as recon-{target}.md including:
- Discovered subdomains and their status
- WAF/CDN information per host
- Technology stack details
- Open ports and services
- Discovered endpoints and URLs
- Recommended next steps based on findings
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 · 50 lines · 17 tokens per session scan A fcffca76eec8
recon is a command published in the GitHub repository ogrodev/fsociety (20 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 530 once invoked, about $0.0001 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 commands, from other repositories
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
connect
Connect to OpenChrome and confirm the MCP server is reachable. Runs a quick health check, reports the Chrome CDP status, and prints the tool surface summary.
browser
Debug and fix browser issues by inspecting, diagnosing, and resolving visual or technical problems.
open
SoDam-Design-Kit open 대시보드 — 검증 이력·판정서·스크린샷을 브라우저로 열람 + 재검증.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.