clarify-task
01Command Claude Code
Break down ambiguous tasks into clear, actionable steps before implementation.
not rated 55
+2 8d ago A 0 tokens
original MIT
55Stars on the repository
202Mods indexed here, across every type
8d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
code-review
02Command Claude Code
Perform a thorough code review that verifies functionality, maintainability, and security before approving a change. Focus on architecture, readability, performance implications, and provide actionable suggestions for improvement.
not rated 55
+2 8d ago A 0 tokens
original MIT
deslop
03Command Claude Code
Source: hamzafer/cursor-commands (MIT).
not rated 55
+2 8d ago A 0 tokens
copy · 94% MIT
diagrams
04Command Claude Code
Analyze the provided code, architecture, or concept and generate a clear, well-structured Mermaid diagram that visualizes the relationships, flow, or structure.
not rated 55
+2 8d ago A 0 tokens
original MIT
final-review
05Command Claude Code
Command "final-review" from adriannoes/awesome-agentic-ai, covering final review - comprehensive pr review & testing, step 0: determine review pass, step 1: create or update the pr, step 2: launch three review agents in parallel and agent 1: codebase consistency reviewer.
not rated 55
+2 8d ago A 0 tokens
original MIT
git-commit
06Command Claude Code
Create a git commit for the current changes using Conventional Commits-style format.
not rated 55
+2 8d ago A 0 tokens
original MIT
Command Claude Code
Execute the full test suite and systematically fix any failures, ensuring code quality and functionality.
not rated 55
+2 8d ago A 0 tokens
original MIT
Command Claude Code
Command "security-audit" from adriannoes/awesome-agentic-ai, covering security audit, steps and security checklist.
not rated 55
+2 8d ago A 0 tokens
original MIT
autopilot
09Command Claude Code
Run autonomous hunt loop on a target — scope check → recon → rank surface → hunt → validate → report with configurable checkpoints. Usage: /autopilot target.com [--paranoid|--normal|--yolo].
not rated 55
+2 8d ago A 45 tokens
original MIT
chain
10Command Claude Code
Build an exploit chain — given bug A, finds B and C to combine for higher severity and payout. Knows common chain patterns: IDOR→ATO, SSRF→cloud metadata, XSS→ATO, open redirect→OAuth theft, S3→bundle→secret→OAuth. Usage: /chain.
not rated 55
+2 8d ago B 62 tokens
copy · 100% MIT
hunt
11Command Claude Code
Active vulnerability hunting. Two-track dispatcher — asks Red Team vs WAPT, hands off to hunt-dispatch skill and sibling commands. Usage: /hunt target.com | /hunt .target.com | /hunt targets.txt [--vuln-class X] [--source-code P] [--chrome].
not rated 55
+2 8d ago A 61 tokens
original MIT
intel
12Command Claude Code
On-demand intelligence fetch for a target — CVEs, disclosed reports, new features. Wraps learn.py + hunt memory context. Usage: /intel target.com.
not rated 55
+2 8d ago A 32 tokens
copy · 100% MIT
memory-gc
13Command Claude Code
Inspect or rotate hunt-memory JSONL files (audit.jsonl, patterns.jsonl, journal.jsonl). Caps file size and keeps N rotated backups so memory does not grow unbounded.
not rated 55
+2 8d ago A 37 tokens
copy · 100% MIT
pickup
14Command Claude Code
Pick up a previous hunt on a target — shows hunt history, untested endpoints, and memory-informed suggestions. Usage: /pickup target.com.
not rated 55
+2 8d ago A 28 tokens
copy · 100% MIT
recon
15Command Claude Code
Run full recon pipeline on a target — subdomain enum (Chaos API + subfinder), live host discovery (dnsx + httpx), URL crawl (katana + waybackurls + gau), gf pattern classification, nuclei scan. Outputs to recon/ / directory. Usage: /recon target.com.
not rated 55
+2 8d ago A 62 tokens
copy · 91% MIT
remember
16Command Claude Code
Log current finding or successful pattern to hunt memory. Auto-fills from /validate output if available. Usage: /remember.
not rated 55
+2 8d ago A 24 tokens
copy · 100% MIT
report
17Command Claude Code
Write a submission-ready bug bounty report. Generates H1/Bugcrowd/Intigriti/Immunefi format with CVSS 3.1 score, proof of concept, impact statement, and remediation. Run /validate first. Usage: /report.
not rated 55
+2 8d ago A 52 tokens
copy · 86% MIT
surface
18Command Claude Code
Show ranked attack surface for a target based on recon output + hunt memory. Invokes recon-ranker agent. Usage: /surface target.com.
not rated 55
+2 8d ago A 28 tokens
copy · 100% MIT
triage
19Command Claude Code
Quick 7-Question Gate triage on a finding before writing a report. Kills N/A submissions before they happen. Faster than /validate — for quick go/no-go decisions. Usage: /triage.
not rated 55
+2 8d ago A 42 tokens
copy · 97% MIT
validate
20Command Claude Code
Validate a finding — runs 7-Question Gate + 4-gate checklist. Kills weak findings before report writing. Prevents N/A submissions that hurt validity ratio. Usage: /validate.
not rated 55
+2 8d ago A 39 tokens
copy · 97% MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: