一键导入
orchestration
Decepticon orchestrator patterns — delegation, state management, adaptive re-planning, context handoff protocols.
菜单
Decepticon orchestrator patterns — delegation, state management, adaptive re-planning, context handoff protocols.
Operational-tier finding template — minimal fields for sub-agent decision support. Heavyweight deliverable promotion lives in skills/decepticon/final-report.
Red team engagement lifecycle management — initiation, phase transitions, go/no-go gates, deconfliction, emergency procedures, completion.
Final engagement report generation — executive summary, technical report, findings aggregation, attack path narrative, detection gap matrix, remediation roadmap.
Exploitation finding documentation — initial access reports, exploit chain documentation, CVSS v4.0 scoring, shell/credential inventory, detection gap analysis.
Post-exploitation finding documentation — credential access, privilege escalation, lateral movement reports, detection gap analysis, attack path documentation, CVSS v4.0 scoring.
Recon output formatting — report structure, CVSS v4.0 scoring (primary), MITRE ATT&CK mapping, finding prioritization, Markdown output, detection gap tracking, handoff checklists.
| name | orchestration |
| description | Decepticon orchestrator patterns — delegation, state management, adaptive re-planning, context handoff protocols. |
| allowed-tools | Read |
| metadata | {"subdomain":"orchestration","when_to_use":"delegate, orchestrate, next objective, blocked, re-plan, hand off, engagement state, status update, parallel execution","tags":"orchestration, delegation, state-management, re-planning, context-handoff","upstream_ref":"Decepticon orchestrator delegation / re-planning patterns — multi-agent control plane, no direct attack technique"} |
Every task() delegation MUST include:
recon/, exploit/)task(
description="""
OBJECTIVE: {objective_id} — {title}
PHASE: {phase}
SCOPE:
- IN: {in_scope_targets}
- OUT: {out_of_scope_targets}
CONTEXT FROM PREVIOUS PHASES:
{relevant_findings_summary}
LESSONS LEARNED:
{known_gotchas}
ACCEPTANCE CRITERIA:
- [ ] {criterion_1}
- [ ] {criterion_2}
Save all results to {phase}/
""",
subagent_type="{agent_name}"
)
| Objective Phase | Sub-Agent | When to Use |
|---|---|---|
| Planning | soundwave | Missing roe.json/conops.json/deconfliction.json, or documents need updating |
| Recon | recon | Subdomain/port/service enumeration, OSINT, cloud/web recon |
| Exploitation | exploit | Initial access: SQLi, SSTI, AD attacks, credential exploitation |
| Post-Exploitation | postexploit | After foothold: cred dump, privesc, lateral movement, C2 |
Delegate independent tasks simultaneously for efficiency:
# Independent targets — run in parallel
task(description="Recon subnet 10.0.0.0/24...", subagent_type="recon")
task(description="Recon subnet 10.0.1.0/24...", subagent_type="recon")
# DO NOT parallelize dependent tasks:
# ✗ Exploit before recon completes
# ✗ PostExploit before foothold established
./
├── plan/
│ ├── roe.json # Immutable scope boundaries (read every iteration)
│ ├── conops.json # Operation concept
│ ├── deconfliction.json # Deconfliction identifiers and procedures
│ └── opplan.json # Objective tracker (update status after each sub-agent)
├── findings/ # Per-finding Markdown files, created lazily
├── lessons_learned.md # Failed approaches + what worked
└── .ralph_state.json # Loop iteration counter + completion flags
passed, blocked, in_progress)findings/FIND-{NNN}.md only when a real finding existsfindings/FIND-*.md entries each iteration (keep only relevant excerpts)Execute this IN ORDER after every recon task() completes. No exceptions.
1. Read recon/SUMMARY.md
├── Missing or empty? → Rule 13 crash protocol (retry once, then BLOCKED)
└── Present → continue
2. Contains RECON_HANDOFF / CRITICAL/HIGH finding / captured session?
├── YES → dispatch task("exploit", ...) IMMEDIATELY (Rule 19)
│ Pass: exact vector, URL, param, session tokens, challenge tags
└── NO (RECON_BUDGET_EXHAUSTED / LOW/INFO only) → continue
3. RECON_BUDGET_EXHAUSTED with zero confirmed vulns?
├── Unvisited surface remains? → focused second recon turn on that surface
└── No unvisited surface → update_objective(status="blocked",
reason="recon exhausted: no confirmed vuln class")
Rule: Step 2 YES has NO exceptions. Do not do "one more recon probe" first.
1. Document failure:
- WHY it failed (specific error, defense mechanism, missing prerequisite)
- WHAT was attempted (tools, techniques, targets)
→ Append to lessons_learned.md
2. Assess alternatives:
- Different attack vector from findings?
- Lower-risk approach?
- Skip and return later after more intel?
3. Decision:
IF alternative exists → delegate new task with adjusted approach
IF prerequisite missing → re-order objectives (e.g., need more recon)
IF no path forward → mark BLOCKED with explanation, move to next objective
The OPPLAN defines priority order, but you may deviate when:
Always document re-ordering decisions in lessons_learned.md.
Report structured status:
| Objective | Phase | Sub-Agent | Result | Key Findings |
|---|---|---|---|---|
| OBJ-001 | Recon | recon | PASSED | 12 subdomains, AD on 10.0.0.5 |
Before each delegation, briefly state:
Maintain running status after each iteration:
Engagement: {name}
Progress: {passed}/{total} objectives
Current: OBJ-003 (Exploit phase)
Blocked: OBJ-002 (WAF blocking SQLi — will retry after credential access)
Next: OBJ-004 (PostExploit — pending OBJ-003 completion)
When all objectives are done: