Agent support · Hooks & Lifecycle

Validate prompts before submission

Intercept user prompts before they reach the model — block, rewrite, redact, annotate, or inject context

Tool-Specific Hooks Hooks & Lifecycle
Supported
Partial
No
Unknown
Claude Code Current · Jun 2026
Cline CLI Current · Jun 2026
Codex CLI Current · Jun 2026
GitHub Copilot CLI Current · Jun 2026
Cursor Current · Jun 2026
2.1.140 - 2.1.197
3.0.0 - 3.0.34
0.131.0 - 0.142.4
1.0.46 - 1.0.66
3.7 - 3.9
2.1.80 - 2.1.139
0.116.0 - 0.130.0
1.0.9 - 1.0.45
3.0 - 3.2
2.1.16 - 2.1.79
0.89.0 - 0.115.0
0.0.389 - 1.0.8
2.4 - 2.5
2.0.77 - 2.1.15
0.78.0 - 0.88.0
0.0.374 - 0.0.388
2.0
1.0.54 - 2.0.76
0.8.0 - 0.77.0
1.7 - 2.0
0.2.31 - 1.0.53
0.2.0 - 0.7.0
0.45 - 1.2

Supported by all 5 agents.

HoverTap any cell for version details.

Agent event mapping

  • claude-code UserPromptSubmit
  • cline UserPromptSubmit
  • codex-cli UserPromptSubmit
  • copilot userPromptSubmitted
  • cursor beforeSubmitPrompt

Sub-capabilities

  • Block prompts that violate policies (PII, secrets, off-topic)
  • Rewrite or augment prompts with additional context
  • Claude Code: receives CWD, transcript ID, prompt text; return value can mutate or block
  • Cursor: returns continue boolean + modified user_message