[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7980YP9SPQ3NX82JYYC786M":3,"skill-same:01M7980YP9SPQ3NX82JYYC786M":50},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":35,"install":36,"resources":49},"01M7980YP9SPQ3NX82JYYC786M","orchestration",null,"Decepticon orchestrator patterns — delegation, state management, adaptive re-planning, context handoff protocols.","7ShIkI3\u002FDecepticon-x-DarkTriad","7ShIkI3","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F78133376?v=4","01M797CTK5AHH2161YVG93NJ3B","Raphael Pascaud","01M797CTKRQS64R01J7E6TJSEM",3,"Apache-2.0","https:\u002F\u002Fgithub.com\u002F7ShIkI3\u002FDecepticon-x-DarkTriad\u002Fblob\u002Fmain\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fdecepticon\u002Forchestration\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: orchestration\ndescription: \"Decepticon orchestrator patterns — delegation, state management, adaptive re-planning, context handoff protocols.\"\nallowed-tools: Read\nmetadata:\n  subdomain: orchestration\n  when_to_use: \"delegate, orchestrate, next objective, blocked, re-plan, hand off, engagement state, status update, parallel execution\"\n  tags: orchestration, delegation, state-management, re-planning, context-handoff\n  upstream_ref: \"Decepticon orchestrator delegation \u002F re-planning patterns — multi-agent control plane, no direct attack technique\"\n---\n\n# Decepticon Orchestration Patterns\n\n## Delegation Protocol\n\n### Context Handoff — What Every Sub-Agent Needs\nEvery `task()` delegation MUST include:\n\n1. **Objective** — What specifically to accomplish (from OPPLAN)\n2. **Scope** — IN SCOPE targets + OUT OF SCOPE boundaries (from RoE)\n3. **Context** — Relevant findings from previous phases\n4. **Lessons** — Known gotchas, failed approaches, OPSEC warnings\n5. **Acceptance Criteria** — How the sub-agent knows it's done\n6. **Output Location** — Where to save results (e.g. `recon\u002F`, `exploit\u002F`)\n\n### Delegation Template\n```\ntask(\n  description=\"\"\"\n  OBJECTIVE: {objective_id} — {title}\n  PHASE: {phase}\n\n  SCOPE:\n  - IN: {in_scope_targets}\n  - OUT: {out_of_scope_targets}\n\n  CONTEXT FROM PREVIOUS PHASES:\n  {relevant_findings_summary}\n\n  LESSONS LEARNED:\n  {known_gotchas}\n\n  ACCEPTANCE CRITERIA:\n  - [ ] {criterion_1}\n  - [ ] {criterion_2}\n\n  Save all results to {phase}\u002F\n  \"\"\",\n  subagent_type=\"{agent_name}\"\n)\n```\n\n### Sub-Agent Selection Matrix\n\n| Objective Phase | Sub-Agent | When to Use |\n|----------------|-----------|-------------|\n| Planning | `soundwave` | Missing roe.json\u002Fconops.json\u002Fdeconfliction.json, or documents need updating |\n| Recon | `recon` | Subdomain\u002Fport\u002Fservice enumeration, OSINT, cloud\u002Fweb recon |\n| Exploitation | `exploit` | Initial access: SQLi, SSTI, AD attacks, credential exploitation |\n| Post-Exploitation | `postexploit` | After foothold: cred dump, privesc, lateral movement, C2 |\n\n### Parallel Execution\nDelegate independent tasks simultaneously for efficiency:\n```\n# Independent targets — run in parallel\ntask(description=\"Recon subnet 10.0.0.0\u002F24...\", subagent_type=\"recon\")\ntask(description=\"Recon subnet 10.0.1.0\u002F24...\", subagent_type=\"recon\")\n\n# DO NOT parallelize dependent tasks:\n# ✗ Exploit before recon completes\n# ✗ PostExploit before foothold established\n```\n\n## State Management\n\n### Engagement State Files\n```\n.\u002F\n├── plan\u002F\n│   ├── roe.json          # Immutable scope boundaries (read every iteration)\n│   ├── conops.json       # Operation concept\n│   ├── deconfliction.json # Deconfliction identifiers and procedures\n│   └── opplan.json       # Objective tracker (update status after each sub-agent)\n├── findings\u002F            # Per-finding Markdown files, created lazily\n├── lessons_learned.md    # Failed approaches + what worked\n└── .ralph_state.json     # Loop iteration counter + completion flags\n```\n\n### State Update Protocol (After Each Sub-Agent Returns)\n1. **Parse result** — Did the sub-agent report PASSED or BLOCKED?\n2. **Update plan\u002Fopplan.json** — Set objective status (`passed`, `blocked`, `in_progress`)\n3. **Record verified findings** — Add `findings\u002FFIND-{NNN}.md` only when a real finding exists\n4. **Append lessons_learned.md** — Record what worked, what failed, and why\n5. **Check completion** — All objectives passed? → Generate summary\n\n### Context Window Budget\n- Read recent `findings\u002FFIND-*.md` entries each iteration (keep only relevant excerpts)\n- Summarize verbose sub-agent outputs before appending to findings\n- Use files on disk as persistent memory — don't rely on conversation history\n\n## After Recon Returns — Decision Tree\n\nExecute this IN ORDER after every recon task() completes. No exceptions.\n\n```\n1. Read recon\u002FSUMMARY.md\n   ├── Missing or empty? → Rule 13 crash protocol (retry once, then BLOCKED)\n   └── Present → continue\n\n2. Contains RECON_HANDOFF \u002F CRITICAL\u002FHIGH finding \u002F captured session?\n   ├── YES → dispatch task(\"exploit\", ...) IMMEDIATELY (Rule 19)\n   │         Pass: exact vector, URL, param, session tokens, challenge tags\n   └── NO (RECON_BUDGET_EXHAUSTED \u002F LOW\u002FINFO only) → continue\n\n3. RECON_BUDGET_EXHAUSTED with zero confirmed vulns?\n   ├── Unvisited surface remains? → focused second recon turn on that surface\n   └── No unvisited surface → update_objective(status=\"blocked\",\n                               reason=\"recon exhausted: no confirmed vuln class\")\n```\n\n**Rule**: Step 2 YES has NO exceptions. Do not do \"one more recon probe\" first.\n\n## Adaptive Re-planning\n\n### When an Objective is BLOCKED\n```\n1. Document failure:\n   - WHY it failed (specific error, defense mechanism, missing prerequisite)\n   - WHAT was attempted (tools, techniques, targets)\n   → Append to lessons_learned.md\n\n2. Assess alternatives:\n   - Different attack vector from findings?\n   - Lower-risk approach?\n   - Skip and return later after more intel?\n\n3. Decision:\n   IF alternative exists → delegate new task with adjusted approach\n   IF prerequisite missing → re-order objectives (e.g., need more recon)\n   IF no path forward → mark BLOCKED with explanation, move to next objective\n```\n\n### Re-ordering Objectives\nThe OPPLAN defines priority order, but you may deviate when:\n- A higher-priority objective depends on a lower-priority one\n- New findings reveal a faster path to the same goal\n- An objective is temporarily blocked and others are actionable\n\nAlways document re-ordering decisions in lessons_learned.md.\n\n## Response Format\n\n### After Each Sub-Agent Completes\nReport structured status:\n\n| Objective | Phase | Sub-Agent | Result | Key Findings |\n|-----------|-------|-----------|--------|-------------|\n| OBJ-001 | Recon | recon | PASSED | 12 subdomains, AD on 10.0.0.5 |\n\n### Decision Transparency\nBefore each delegation, briefly state:\n- **Why** this objective is next (priority, dependency, re-plan reason)\n- **Which** sub-agent and why\n- **What** context you're passing\n\n### Progress Summary\nMaintain running status after each iteration:\n```\nEngagement: {name}\nProgress: {passed}\u002F{total} objectives\nCurrent: OBJ-003 (Exploit phase)\nBlocked: OBJ-002 (WAF blocking SQLi — will retry after credential access)\nNext: OBJ-004 (PostExploit — pending OBJ-003 completion)\n```\n\n### Engagement Completion Report\nWhen all objectives are done:\n1. Full attack path (every hop, credential, escalation)\n2. Credential inventory\n3. Host access map\n4. Recommendations for defensive improvements\n","# Decepticon Orchestration Patterns\n\n## Delegation Protocol\n\n### Context Handoff — What Every Sub-Agent Needs\nEvery `task()` delegation MUST include:\n\n1. **Objective** — What specifically to accomplish (from OPPLAN)\n2. **Scope** — IN SCOPE targets + OUT OF SCOPE boundaries (from RoE)\n3. **Context** — Relevant findings from previous phases\n4. **Lessons** — Known gotchas, failed approaches, OPSEC warnings\n5. **Acceptance Criteria** — How the sub-agent knows it's done\n6. **Output Location** — Where to save results (e.g. `recon\u002F`, `exploit\u002F`)\n\n### Delegation Template\n```\ntask(\n  description=\"\"\"\n  OBJECTIVE: {objective_id} — {title}\n  PHASE: {phase}\n\n  SCOPE:\n  - IN: {in_scope_targets}\n  - OUT: {out_of_scope_targets}\n\n  CONTEXT FROM PREVIOUS PHASES:\n  {relevant_findings_summary}\n\n  LESSONS LEARNED:\n  {known_gotchas}\n\n  ACCEPTANCE CRITERIA:\n  - [ ] {criterion_1}\n  - [ ] {criterion_2}\n\n  Save all results to {phase}\u002F\n  \"\"\",\n  subagent_type=\"{agent_name}\"\n)\n```\n\n### Sub-Agent Selection Matrix\n\n| Objective Phase | Sub-Agent | When to Use |\n|----------------|-----------|-------------|\n| Planning | `soundwave` | Missing roe.json\u002Fconops.json\u002Fdeconfliction.json, or documents need updating |\n| Recon | `recon` | Subdomain\u002Fport\u002Fservice enumeration, OSINT, cloud\u002Fweb recon |\n| Exploitation | `exploit` | Initial access: SQLi, SSTI, AD attacks, credential exploitation |\n| Post-Exploitation | `postexploit` | After foothold: cred dump, privesc, lateral movement, C2 |\n\n### Parallel Execution\nDelegate independent tasks simultaneously for efficiency:\n```\n# Independent targets — run in parallel\ntask(description=\"Recon subnet 10.0.0.0\u002F24...\", subagent_type=\"recon\")\ntask(description=\"Recon subnet 10.0.1.0\u002F24...\", subagent_type=\"recon\")\n\n# DO NOT parallelize dependent tasks:\n# ✗ Exploit before recon completes\n# ✗ PostExploit before foothold established\n```\n\n## State Management\n\n### Engagement State Files\n```\n.\u002F\n├── plan\u002F\n│   ├── roe.json          # Immutable scope boundaries (read every iteration)\n│   ├── conops.json       # Operation concept\n│   ├── deconfliction.json # Deconfliction identifiers and procedures\n│   └── opplan.json       # Objective tracker (update status after each sub-agent)\n├── findings\u002F            # Per-finding Markdown files, created lazily\n├── lessons_learned.md    # Failed approaches + what worked\n└── .ralph_state.json     # Loop iteration counter + completion flags\n```\n\n### State Update Protocol (After Each Sub-Agent Returns)\n1. **Parse result** — Did the sub-agent report PASSED or BLOCKED?\n2. **Update plan\u002Fopplan.json** — Set objective status (`passed`, `blocked`, `in_progress`)\n3. **Record verified findings** — Add `findings\u002FFIND-{NNN}.md` only when a real finding exists\n4. **Append lessons_learned.md** — Record what worked, what failed, and why\n5. **Check completion** — All objectives passed? → Generate summary\n\n### Context Window Budget\n- Read recent `findings\u002FFIND-*.md` entries each iteration (keep only relevant excerpts)\n- Summarize verbose sub-agent outputs before appending to findings\n- Use files on disk as persistent memory — don't rely on conversation history\n\n## After Recon Returns — Decision Tree\n\nExecute this IN ORDER after every recon task() completes. No exceptions.\n\n```\n1. Read recon\u002FSUMMARY.md\n   ├── Missing or empty? → Rule 13 crash protocol (retry once, then BLOCKED)\n   └── Present → continue\n\n2. Contains RECON_HANDOFF \u002F CRITICAL\u002FHIGH finding \u002F captured session?\n   ├── YES → dispatch task(\"exploit\", ...) IMMEDIATELY (Rule 19)\n   │         Pass: exact vector, URL, param, session tokens, challenge tags\n   └── NO (RECON_BUDGET_EXHAUSTED \u002F LOW\u002FINFO only) → continue\n\n3. RECON_BUDGET_EXHAUSTED with zero confirmed vulns?\n   ├── Unvisited surface remains? → focused second recon turn on that surface\n   └── No unvisited surface → update_objective(status=\"blocked\",\n                               reason=\"recon exhausted: no confirmed vuln class\")\n```\n\n**Rule**: Step 2 YES has NO exceptions. Do not do \"one more recon probe\" first.\n\n## Adaptive Re-planning\n\n### When an Objective is BLOCKED\n```\n1. Document failure:\n   - WHY it failed (specific error, defense mechanism, missing prerequisite)\n   - WHAT was attempted (tools, techniques, targets)\n   → Append to lessons_learned.md\n\n2. Assess alternatives:\n   - Different attack vector from findings?\n   - Lower-risk approach?\n   - Skip and return later after more intel?\n\n3. Decision:\n   IF alternative exists → delegate new task with adjusted approach\n   IF prerequisite missing → re-order objectives (e.g., need more recon)\n   IF no path forward → mark BLOCKED with explanation, move to next objective\n```\n\n### Re-ordering Objectives\nThe OPPLAN defines priority order, but you may deviate when:\n- A higher-priority objective depends on a lower-priority one\n- New findings reveal a faster path to the same goal\n- An objective is temporarily blocked and others are actionable\n\nAlways document re-ordering decisions in lessons_learned.md.\n\n## Response Format\n\n### After Each Sub-Agent Completes\nReport structured status:\n\n| Objective | Phase | Sub-Agent | Result | Key Findings |\n|-----------|-------|-----------|--------|-------------|\n| OBJ-001 | Recon | recon | PASSED | 12 subdomains, AD on 10.0.0.5 |\n\n### Decision Transparency\nBefore each delegation, briefly state:\n- **Why** this objective is next (priority, dependency, re-plan reason)\n- **Which** sub-agent and why\n- **What** context you're passing\n\n### Progress Summary\nMaintain running status after each iteration:\n```\nEngagement: {name}\nProgress: {passed}\u002F{total} objectives\nCurrent: OBJ-003 (Exploit phase)\nBlocked: OBJ-002 (WAF blocking SQLi — will retry after credential access)\nNext: OBJ-004 (PostExploit — pending OBJ-003 completion)\n```\n\n### Engagement Completion Report\nWhen all objectives are done:\n1. Full attack path (every hop, credential, escalation)\n2. Credential inventory\n3. Host access map\n4. Recommendations for defensive improvements\n",{"name":5,"metadata":24,"description":7,"allowed-tools":28},{"tags":25,"subdomain":5,"when_to_use":26,"upstream_ref":27},"orchestration, delegation, state-management, re-planning, context-handoff","delegate, orchestrate, next objective, blocked, re-plan, hand off, engagement state, status update, parallel execution","Decepticon orchestrator delegation \u002F re-planning patterns — multi-agent control plane, no direct attack technique","Read","main","42b918525fb79065e730da3da997bffb33fcd414","packages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fdecepticon\u002Forchestration",0,"https:\u002F\u002Fgithub.com\u002F7ShIkI3\u002FDecepticon-x-DarkTriad","https:\u002F\u002Fgithub.com\u002F7ShIkI3","2026-07-22 19:02:27",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add 7ShIkI3\u002FDecepticon-x-DarkTriad --skill orchestration",{"tool":42,"command":43},"bunx","bunx skills add 7ShIkI3\u002FDecepticon-x-DarkTriad --skill orchestration",{"tool":45,"command":46},"pnpm","pnpm dlx skills add 7ShIkI3\u002FDecepticon-x-DarkTriad --skill orchestration","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F7ShIkI3\u002FDecepticon-x-DarkTriad\u002Fblob\u002Fmain\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fdecepticon\u002Forchestration\u002FSKILL.md",true,[],[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":19},"01M798TNHEBA4Y67TJJ7W0KBDD","wps-pixie-dust","WPS Pixie-Dust offline nonce attack (reaver -K \u002F pixiewps) and fallback online PIN brute (bully) to recover the AP's WPA PSK without capturing a handshake.","https:\u002F\u002Fgithub.com\u002F7ShIkI3\u002FDecepticon-x-DarkTriad\u002Fblob\u002Fmain\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fwireless\u002Fwps-pixie-dust\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M798TH79VR8XM7AAMG0ZKSXX","wpa3-sae","WPA3-SAE transition-mode downgrade (DragonShift), SSID Confusion CVE-2023-52424, Dragonblood side-channels, and SAE captive-portal credential recovery against WPA3-Personal networks.","https:\u002F\u002Fgithub.com\u002F7ShIkI3\u002FDecepticon-x-DarkTriad\u002Fblob\u002Fmain\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fwireless\u002Fwpa3-sae\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M798TD0E10ZHQN5X362M4HG9","wpa2-psk","WPA\u002FWPA2-PSK handshake capture via targeted deauth + PMKID (no deauth required) + offline hashcat cracking. The most common consumer\u002FSMB encryption mode in 2026.","https:\u002F\u002Fgithub.com\u002F7ShIkI3\u002FDecepticon-x-DarkTriad\u002Fblob\u002Fmain\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fwireless\u002Fwpa2-psk\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M798T7HFR3NB9WJTK1FESVF9","wpa-enterprise-eap","WPA\u002FWPA2\u002FWPA3-Enterprise (802.1X\u002FEAP) rogue-RADIUS evil-twin for MSCHAPv2 capture, GTC downgrade, and PEAP relay. MSCHAPv2 capture equals a NetNTLM hash — the primary wireless on-ramp to Active Directory.","https:\u002F\u002Fgithub.com\u002F7ShIkI3\u002FDecepticon-x-DarkTriad\u002Fblob\u002Fmain\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fwireless\u002Fwpa-enterprise-eap\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M798T38B4SV0T87VQK56KPHC","krack-fragattacks","KRACK key-reinstallation (CVE-2017-13077..13082) and FragAttacks fragmentation\u002Faggregation flaws (CVE-2020-24586..24588, CVE-2020-26139..26147) against legacy or embedded 802.11 supplicants with poor patch cadence.","https:\u002F\u002Fgithub.com\u002F7ShIkI3\u002FDecepticon-x-DarkTriad\u002Fblob\u002Fmain\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fwireless\u002Fkrack-fragattacks\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M798SXTNF0RP1DXKQEWFVQ9H","evil-twin-karma","Evil-twin rogue AP with KARMA\u002FMana PNL-probe response, captive-portal credential capture, and post-association MITM for PSK\u002Fopen networks. Distinct from wpa-enterprise-eap which targets 802.1X.","https:\u002F\u002Fgithub.com\u002F7ShIkI3\u002FDecepticon-x-DarkTriad\u002Fblob\u002Fmain\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fwireless\u002Fevil-twin-karma\u002FSKILL.md",[],[]]