KittyProxy and Autonomous Agent

The agent coordinates discovery, module selection, reasoning, replay, and campaign output from the active workspace. Use it after scope, hosts, and proxy captures are already defined.

Preflight

workspace use web-recon
agent doctor
proxy status
scope list

Resolve missing prerequisites before running an agent campaign. The agent should not infer scope from a URL alone when a workspace scope already exists.

Reconnaissance Only

agent http://127.0.0.1 --no-exploit --goal recon --safety-profile discreet

This mode plans and runs non-exploit discovery. It is the default starting point for authorized web assessments.

Reuse KittyProxy Flows

agent http://127.0.0.1 \
  --no-exploit \
  --reuse-proxy-auth \
  --proxy-flow-limit 40

Proxy reuse imports captured cookies, endpoints, forms, and parameters. This gives the agent authenticated context without storing credentials in module options.

Planning And Dry Run

agent http://127.0.0.1 --no-exploit --plan-only --verbose
agent http://127.0.0.1 --profile safe-web --dry-run

Active Validation

agent http://127.0.0.1 \
  --goal validate \
  --approve-risk active \
  --safety-profile normal \
  --max-modules 20 \
  --threads 5

Risk levels are incremental: read, active, intrusive, destructive. Use only the level explicitly allowed by the mandate.

Campaign Trace

agent explain <run_id>
agent replay <run_id>
agent retest <finding_id>
agent --resume <run_id>
agent metadata <run_id>
campaign --preview

Keep the run_id. It links agent decisions, module executions, findings, and campaign output.

Troubleshooting