/op-campaign

description: Resume or execute an opsec campaign with progress tracking
allowed-tools: Bash, Read, Write, Glob, Grep, Task, AskUserQuestion
argument-hint: [resume | status | next | complete-step | complete-phase | reset | note <text>]

> **Storage Policy**: ALL output files MUST be saved in the project directory. NEVER write to /tmp/ or any system temporary directory.

Campaign Runner

Subcommand: `$ARGUMENTS`

Orchestrator Rules (YOU must follow these)

• YOU are the orchestrator. YOU stay at <30% context usage
• Each executor subagent gets 100% fresh context via Task tool
• NEVER run offensive tools yourself — ALWAYS delegate to subagent executors

Dispatch

• **status**: `node "${CLAUDE_PLUGIN_ROOT}/scripts/session-state.js" show`
• **resume**: `node "${CLAUDE_PLUGIN_ROOT}/scripts/session-state.js" smart-resume` and act on recommendation
• **next**: Spawn fresh Task subagent executor for the next step. Pass full context: operation, target, current phase, step number, tool instructions, output format requirements
• **complete-step**: `node "${CLAUDE_PLUGIN_ROOT}/scripts/session-state.js" complete-step --summary "<summary>"`
• **complete-phase**: `node "${CLAUDE_PLUGIN_ROOT}/scripts/session-state.js" complete-phase --summary "<summary>"`
• **reset**: `node "${CLAUDE_PLUGIN_ROOT}/scripts/session-state.js" reset`
• **note <text>**: `node "${CLAUDE_PLUGIN_ROOT}/scripts/session-state.js" add-note "<text>"`

Executor Subagent Template

When spawning a Task executor for "next", include: 1. Operation name and target 2. Current phase and step details 3. Exact tools to use and in what order 4. Expected output format: RESULT, OPS_COUNT, SUMMARY, ALERTS, NEXT_RECOMMENDATION 5. Storage policy reminder 6. Script paths for logging results

After Each Step

Collect executor's output. Parse results. Update state. Ask user to continue or adjust.