triage
25Clear-Capabilities/agentic-security
Command
Interactive triage. Mark each finding TP / FP / wontfix. Feeds the active-learning loop for next scan.
87 3d ago A 24 tokens
SessionStart
26Clear-Capabilities/agentic-security
Hook
Runs when a session starts, executing session-welcome.js, session-start-self-check.js and session-start-model-capture.js via node (3 commands). From Clear-Capabilities/agentic-security.
87 3d ago A
tokens not measured
Clear-Capabilities/agentic-security
Hook
Runs when you submit a prompt, before the agent sees it, executing dispatch-user-prompt.js via node. From Clear-Capabilities/agentic-security.
87 3d ago A
tokens not measured
PreToolUse
28Clear-Capabilities/agentic-security
Hook
Runs before the agent uses a tool for Edit, Write, MultiEdit and Bash tool calls, executing dispatch-pre-tool.js and pre-bash-guard.js via node (2 commands). From Clear-Capabilities/agentic-security.
87 3d ago A
tokens not measured
PostToolUse
29Clear-Capabilities/agentic-security
Hook
Runs after a tool call finishes for Edit, Write and MultiEdit tool calls, executing post-edit-scan.js via node. From Clear-Capabilities/agentic-security.
87 3d ago A
tokens not measured
Stop
30Clear-Capabilities/agentic-security
Hook
Runs when the agent finishes a response, executing session-stop-drift-check.js via node. From Clear-Capabilities/agentic-security.
87 3d ago A
tokens not measured
Clear-Capabilities/agentic-security
Skill Claude CodeCodex
Walk through the six-step recipe for adding a new SAST detector — pick the module, export scan(), wire, fixture, test.
87 3d ago A 36 tokens
Clear-Capabilities/agentic-security
Skill Claude CodeCodex
Privacy review before handling user data. Activate on PII/PHI/PCI shapes (email, SSN, CC, MRN). Writes DATAFLOW.md.
87 3d ago A 41 tokens
Clear-Capabilities/agentic-security
Skill Claude CodeCodex
Guard risky writes. Activate before eval/exec, string-concat SQL, md5/sha1/DES/RC4 crypto, or auth/jwt/oauth/cipher.
87 3d ago A 45 tokens
Clear-Capabilities/agentic-security
Skill Claude CodeCodex
Explain or teach a vuln. Activate on a CVE/GHSA id, "what is this vuln", "explain finding", or a Socratic walkthrough.
87 3d ago A 42 tokens
Clear-Capabilities/agentic-security
Skill Claude CodeCodex
Apply a remediation patch via the deterministic MCP toolchain. Activate when user asks to fix a scanner finding.
87 3d ago A 31 tokens
Clear-Capabilities/agentic-security
Skill Claude CodeCodex
Rotate a leaked secret end-to-end. Activate on leaked API key, exposed credential, or pushed-secret reports.
87 3d ago A 32 tokens
Clear-Capabilities/agentic-security
Skill Claude CodeCodex
Run the security scanner. Activate on ship / deploy / launch / "is this safe?" — before the deploy happens.
87 3d ago A 35 tokens