Run the monitoring agent: $ARGUMENTS
Parse the mode from arguments:
- If empty or "baseline": Run monitor agent with prompt "Baseline mode. Capture the current state of all in-scope targets. Use recon/ data if available for a richer baseline."
- If "check": Run monitor agent with prompt "Check mode. Compare current state against baselines in monitor/. Report all changes and recommend which agents to re-run."
- If "scope": Run monitor agent with prompt "Scope mode. Use MCP get_program_scope to check if the platform has updated the program scope. Diff against local scope.yaml and report new assets."
After the agent completes:
- If changes were found, show a summary and suggest next actions
- If scope changes were found, ask if the user wants to run /pipeline on new assets
- Log to brain:
uv run python3 ../../tools/brain.py log "Monitor {mode}: {summary}"
Top-Tier Monitoring Bar
Treat changes as vulnerability triggers.
- New host: run scope check, tech fingerprint, and surface ranking.
- New endpoint: diff auth requirement, methods, content types, and response schemas against siblings.
- New JS bundle: extract routes, API clients, feature flags, source maps, and changed sinks.
- New policy/scope text: update safe-harbor headers, prohibited actions, asset tiers, payout exclusions, and credential rules.
- Fixed finding: verify remediation without bypass attempts unless authorized, then record the patch pattern for future dupcheck.
Prioritize changes touching auth, billing, admin, integrations, uploads, exports, webhooks, OAuth, AI/tool execution, and tenant boundaries.
1---2name: monitor-23description: Monitor targets for changes. Usage: /monitor baseline (first run), /monitor check (detect changes), /monitor scope (check platform for scope updates)4---56Run the monitoring agent: $ARGUMENTS78Parse the mode from arguments:9- If empty or "baseline": Run monitor agent with prompt "Baseline mode. Capture the current state of all in-scope targets. Use recon/ data if available for a richer baseline."10- If "check": Run monitor agent with prompt "Check mode. Compare current state against baselines in monitor/. Report all changes and recommend which agents to re-run."11- If "scope": Run monitor agent with prompt "Scope mode. Use MCP get_program_scope to check if the platform has updated the program scope. Diff against local scope.yaml and report new assets."1213After the agent completes:141. If changes were found, show a summary and suggest next actions152. If scope changes were found, ask if the user wants to run /pipeline on new assets163. Log to brain: `uv run python3 ../../tools/brain.py log "Monitor {mode}: {summary}"`1718## Top-Tier Monitoring Bar1920Treat changes as vulnerability triggers.2122- New host: run scope check, tech fingerprint, and surface ranking.23- New endpoint: diff auth requirement, methods, content types, and response schemas against siblings.24- New JS bundle: extract routes, API clients, feature flags, source maps, and changed sinks.25- New policy/scope text: update safe-harbor headers, prohibited actions, asset tiers, payout exclusions, and credential rules.26- Fixed finding: verify remediation without bypass attempts unless authorized, then record the patch pattern for future dupcheck.2728Prioritize changes touching auth, billing, admin, integrations, uploads, exports, webhooks, OAuth, AI/tool execution, and tenant boundaries.
h-mmer