with one click
engagement-lifecycle
Red team engagement lifecycle management — initiation, phase transitions, go/no-go gates, deconfliction, emergency procedures, completion.
Menu
Red team engagement lifecycle management — initiation, phase transitions, go/no-go gates, deconfliction, emergency procedures, completion.
Drive Decepticon — an autonomous multi-agent red-team framework — over MCP to run authorized penetration tests and bug-bounty engagements end to end, then watch and steer them live from chat. Launch an engagement against a target, poll its transcript to narrate progress, send messages to refocus it, and pull findings as SARIF. Use when the user asks to run a pentest/red-team engagement, hunt a bug bounty, do recon, exploit/scan a host, web app, API, network, cloud, Active Directory, mobile app, or smart contract WITH Decepticon — or to check/resume a running engagement or report what Decepticon found. Triggers: run a decepticon engagement, pentest this with decepticon, bug bounty, recon this target, red team this, scan this host, resume the engagement, what did decepticon find, decepticon status. Do NOT use for ad-hoc local tool runs (running nmap/sqlmap/ffuf directly) when no Decepticon server is involved — this drives the Decepticon orchestrator, not raw tools.
IoT device security reconnaissance — firmware extraction, embedded analysis, protocol identification, default credential checking, vulnerability scanning, device fingerprinting.
Mobile application security reconnaissance — APK/IPA analysis, permission enumeration, certificate validation, hardcoded secret detection, insecure storage identification, network security analysis.
Wireless network security reconnaissance — WiFi analysis, Bluetooth assessment, RFID/NFC evaluation, signal capture, protocol analysis, encryption testing, rogue device detection.
Operational-tier finding template — minimal fields for sub-agent decision support. Heavyweight deliverable promotion lives in skills/decepticon/final-report.
Final engagement report generation — executive summary, technical report, findings aggregation, attack path narrative, detection gap matrix, remediation roadmap.
| name | engagement-lifecycle |
| description | Red team engagement lifecycle management — initiation, phase transitions, go/no-go gates, deconfliction, emergency procedures, completion. |
| allowed-tools | Read |
| metadata | {"subdomain":"orchestration","when_to_use":"start engagement, new engagement, engagement status, phase transition, go/no-go, deconfliction, emergency stop, engagement complete, wrap up","tags":"engagement, lifecycle, planning, phase-transition, deconfliction, emergency, completion","upstream_ref":"Decepticon engagement lifecycle — orchestrator-level planning skill, no direct attack technique"} |
Before starting any engagement, verify:
Documents exist and are valid:
roe.json — Rules of Engagement with scope, restrictions, contactsconops.json — Concept of Operations with threat profile and kill chain phasesdeconfliction.json — Deconfliction identifiers and proceduresopplan.json — Operational Plan with sequenced, acceptance-gated objectivesInfrastructure ready:
nc -z c2-sliver 31337 (gRPC port)/workspace/.sliver-configs/decepticon.cfg<engagement>/recon/, <engagement>/exploit/, etc.)If any document is missing: Delegate to soundwave sub-agent first.
All paths below are relative to the engagement working directory (set via cd before commands run).
| Type | Starting Phase | Sub-Agents Used | Key Consideration |
|---|---|---|---|
| Full Scope | Planning → Recon | All (soundwave, recon, exploit, postexploit) | Longest duration, most OPSEC-sensitive |
| Assumed Breach | Exploitation | exploit, postexploit | Skip recon, start from provided foothold |
| Recon Only | Recon | recon only | No exploitation, intelligence gathering only |
| Objective-Based | Varies | Targeted subset | Focus on specific crown jewels |
Read plan/roe.json to determine engagement type and adjust phase ordering accordingly.
Before transitioning between phases, verify the gate criteria from the workflow skill:
Planning → Recon: roe.json + conops.json + deconfliction.json + opplan.json exist and validated
Recon → Exploit: Attack surface identified, targets prioritized, vulns catalogued
Exploit → PostExploit: Initial foothold established, access type documented
PostExploit → Report: All OPPLAN objectives resolved (passed or blocked)
workflow skill for phase-specific gates)Some objectives may uncover new targets or invalidate assumptions:
If roe.json specifies deconfliction contacts:
timeline.jsonl only when a real event occursIf engagement must be halted:
timeline.jsonl and update the affected OPPLAN objectivesTrack these throughout the engagement for the final report:
| Metric | Description | Source |
|---|---|---|
| MTTD | Mean Time to Detect (per objective) | Blue team detection timestamps |
| Dwell Time | Time from foothold to detection | timeline.jsonl timestamps |
| Objectives Completed | Passed / Total | opplan.json status counts |
| Attack Path Depth | Number of hops from initial access | lateral movement log |
| Credential Exposure | Unique credentials captured | post-exploit/creds/ |
When all objectives are resolved:
Attack Path Documentation:
Findings Synthesis:
<engagement>/findings/FIND-*.md entriesRemediation Recommendations:
Evidence Preservation:
<engagement>/recon/<engagement>/exploit/<engagement>/post-exploit/Cleanup: