[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M730QXXACT4AS8VHJ3MZ20H4":3,"skill-same:01M730QXXACT4AS8VHJ3MZ20H4":51},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M730QXXACT4AS8VHJ3MZ20H4","bft-consensus-patterns",null,"Implement Byzantine Fault Tolerant voting for critical agent decisions. 3-of-N quorum for infrastructure writes, reputation-weighted voting, dual-verification pipelines, and automatic privilege demotion.","Horonomos-laps\u002FYana-AI","Horonomos-laps","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F355299122?v=4","01M76B3QPXE88ET2SQPDPVATZT"," Horonomos-laps","01M72ZQRJPCYPSSWT4D00VJR2A",13,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fbft-consensus-patterns\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: bft-consensus-patterns\ndescription: Implement Byzantine Fault Tolerant voting for critical agent decisions. 3-of-N quorum for infrastructure writes, reputation-weighted voting, dual-verification pipelines, and automatic privilege demotion.\norigin: PBFT (Castro & Liskov 1999), Raft (Ongaro & Ousterhout 2014), YAMTAM rule 54\nlicense: Apache-2.0\nversion: 1.0.0\ncompatibility: claude-sonnet-4-6, claude-opus-4-7\n---\n\n# Byzantine Fault Tolerant Consensus\n\nA swarm of 87 agents can tolerate up to 28 simultaneous compromised agents (f = ⌊(N-1)\u002F3⌋) if decisions require 2f+1 votes.\n\n## When to Use\n\n- Critical operations that no single agent should decide unilaterally (rule changes, deploys, key rotation)\n- Detecting when a minority of agents have been compromised or are producing incorrect output\n- Dual-verification of important task results (two agents must agree before result is accepted)\n- Enforcing quorum requirements before high-privilege Swarm Bus commands\n\n## Do NOT use for\n\n- Routine read-only operations (overhead not worth it for non-critical tasks)\n- Single-agent systems or development environments\n\n## BFT Voting via SwarmRouter\n\n```js\nimport { SwarmRouter } from 'core\u002Fbus\u002Fswarm-router.js';\n\nconst router = new SwarmRouter();\n\n\u002F\u002F Register voters\n['auditor-1', 'auditor-2', 'auditor-3', 'orch-1', 'orch-2'].forEach(id =>\n  router.register(id, { role: 'auditor', trustScore: 90 })\n);\n\n\u002F\u002F Propose a critical change\nasync function proposeChange(proposerId, change) {\n  const QUORUM = 3;\n  const votes = await Promise.allSettled(\n    [...router.agents.keys()]\n      .filter(id => id !== proposerId)\n      .slice(0, 5)\n      .map(id => router.route({\n        from: proposerId, to: id,\n        command: 'VOTE_REQUEST',\n        payload: { change, fingerprint: router._fingerprint(change) }\n      }))\n  );\n\n  const yesVotes = votes.filter(v => v.status === 'fulfilled' && v.value.delivered).length;\n  if (yesVotes \u003C QUORUM) throw new Error(`CONSENSUS_FAIL: ${yesVotes}\u002F${QUORUM} votes`);\n  return { approved: true, votes: yesVotes };\n}\n```\n\n## Dual-Verification Pipeline (Lớp 79)\n\n```js\n\u002F\u002F Run same task on two independent agents, compare results\nasync function dualVerify(task, agentA, agentB) {\n  const [resultA, resultB] = await Promise.all([\n    runAgent(agentA, task),\n    runAgent(agentB, task),\n  ]);\n\n  const hashA = sha256(JSON.stringify(resultA));\n  const hashB = sha256(JSON.stringify(resultB));\n\n  if (hashA !== hashB) {\n    \u002F\u002F Results diverged — trigger investigation\n    router.penalize(agentA, 10, 'DUAL_VERIFY_DIVERGENCE');\n    router.penalize(agentB, 10, 'DUAL_VERIFY_DIVERGENCE');\n    throw new Error('DUAL_VERIFY_FAIL: agent outputs diverged');\n  }\n  return resultA;\n}\n```\n\n## Reputation-Weighted Voting\n\n```js\nfunction weightedQuorum(voters, minTrustScore = 60) {\n  const eligible = voters.filter(a => a.trustScore >= minTrustScore && !a.quarantined);\n  const totalWeight = eligible.reduce((sum, a) => sum + a.trustScore, 0);\n  const threshold = totalWeight * 0.67;  \u002F\u002F 67% weighted majority\n\n  return { eligible: eligible.length, threshold, totalWeight };\n}\n```\n\n## Automated Privilege Demotion (Lớp 80)\n\n```js\n\u002F\u002F When task transitions to PENDING_APPROVAL state:\nfunction demoteToMinPrivilege(agentId) {\n  const agent = router.agents.get(agentId);\n  \u002F\u002F Restrict allowed commands to read-only subset\n  agent.allowedCommands = new Set(['git status', 'ls', 'cat']);\n  agent.role = 'observer';  \u002F\u002F no write access\n  router._log('PRIVILEGE_DEMOTE', agentId, { reason: 'PENDING_APPROVAL' });\n}\n```\n\n## Agent Heartbeat Interrogation (Lớp 72)\n\n```js\n\u002F\u002F Periodic challenge: agents must respond with correct HMAC\nsetInterval(() => {\n  for (const [id, agent] of router.agents) {\n    const challenge = randomBytes(16).toString('hex');\n    const expectedResponse = hmac256(challenge, agent.sharedSecret);\n\n    sendChallenge(id, challenge).then(response => {\n      if (response !== expectedResponse) {\n        router.quarantine(id, 'HEARTBEAT_FAIL');\n      }\n    }).catch(() => {\n      router.quarantine(id, 'HEARTBEAT_TIMEOUT');\n    });\n  }\n}, 30000);\n```\n\n## Anti-Fake-Pass Checklist\n\n- [ ] QUORUM value ≥ 3 — never use `QUORUM = 1` even temporarily\n- [ ] Quarantined agents excluded from voter pool\n- [ ] Stale agents (heartbeat > TTL) excluded from voter pool\n- [ ] Dual-verify divergence investigated — not silently retried\n- [ ] Vote results logged to Merkle audit chain with fingerprints\n","# Byzantine Fault Tolerant Consensus\n\nA swarm of 87 agents can tolerate up to 28 simultaneous compromised agents (f = ⌊(N-1)\u002F3⌋) if decisions require 2f+1 votes.\n\n## When to Use\n\n- Critical operations that no single agent should decide unilaterally (rule changes, deploys, key rotation)\n- Detecting when a minority of agents have been compromised or are producing incorrect output\n- Dual-verification of important task results (two agents must agree before result is accepted)\n- Enforcing quorum requirements before high-privilege Swarm Bus commands\n\n## Do NOT use for\n\n- Routine read-only operations (overhead not worth it for non-critical tasks)\n- Single-agent systems or development environments\n\n## BFT Voting via SwarmRouter\n\n```js\nimport { SwarmRouter } from 'core\u002Fbus\u002Fswarm-router.js';\n\nconst router = new SwarmRouter();\n\n\u002F\u002F Register voters\n['auditor-1', 'auditor-2', 'auditor-3', 'orch-1', 'orch-2'].forEach(id =>\n  router.register(id, { role: 'auditor', trustScore: 90 })\n);\n\n\u002F\u002F Propose a critical change\nasync function proposeChange(proposerId, change) {\n  const QUORUM = 3;\n  const votes = await Promise.allSettled(\n    [...router.agents.keys()]\n      .filter(id => id !== proposerId)\n      .slice(0, 5)\n      .map(id => router.route({\n        from: proposerId, to: id,\n        command: 'VOTE_REQUEST',\n        payload: { change, fingerprint: router._fingerprint(change) }\n      }))\n  );\n\n  const yesVotes = votes.filter(v => v.status === 'fulfilled' && v.value.delivered).length;\n  if (yesVotes \u003C QUORUM) throw new Error(`CONSENSUS_FAIL: ${yesVotes}\u002F${QUORUM} votes`);\n  return { approved: true, votes: yesVotes };\n}\n```\n\n## Dual-Verification Pipeline (Lớp 79)\n\n```js\n\u002F\u002F Run same task on two independent agents, compare results\nasync function dualVerify(task, agentA, agentB) {\n  const [resultA, resultB] = await Promise.all([\n    runAgent(agentA, task),\n    runAgent(agentB, task),\n  ]);\n\n  const hashA = sha256(JSON.stringify(resultA));\n  const hashB = sha256(JSON.stringify(resultB));\n\n  if (hashA !== hashB) {\n    \u002F\u002F Results diverged — trigger investigation\n    router.penalize(agentA, 10, 'DUAL_VERIFY_DIVERGENCE');\n    router.penalize(agentB, 10, 'DUAL_VERIFY_DIVERGENCE');\n    throw new Error('DUAL_VERIFY_FAIL: agent outputs diverged');\n  }\n  return resultA;\n}\n```\n\n## Reputation-Weighted Voting\n\n```js\nfunction weightedQuorum(voters, minTrustScore = 60) {\n  const eligible = voters.filter(a => a.trustScore >= minTrustScore && !a.quarantined);\n  const totalWeight = eligible.reduce((sum, a) => sum + a.trustScore, 0);\n  const threshold = totalWeight * 0.67;  \u002F\u002F 67% weighted majority\n\n  return { eligible: eligible.length, threshold, totalWeight };\n}\n```\n\n## Automated Privilege Demotion (Lớp 80)\n\n```js\n\u002F\u002F When task transitions to PENDING_APPROVAL state:\nfunction demoteToMinPrivilege(agentId) {\n  const agent = router.agents.get(agentId);\n  \u002F\u002F Restrict allowed commands to read-only subset\n  agent.allowedCommands = new Set(['git status', 'ls', 'cat']);\n  agent.role = 'observer';  \u002F\u002F no write access\n  router._log('PRIVILEGE_DEMOTE', agentId, { reason: 'PENDING_APPROVAL' });\n}\n```\n\n## Agent Heartbeat Interrogation (Lớp 72)\n\n```js\n\u002F\u002F Periodic challenge: agents must respond with correct HMAC\nsetInterval(() => {\n  for (const [id, agent] of router.agents) {\n    const challenge = randomBytes(16).toString('hex');\n    const expectedResponse = hmac256(challenge, agent.sharedSecret);\n\n    sendChallenge(id, challenge).then(response => {\n      if (response !== expectedResponse) {\n        router.quarantine(id, 'HEARTBEAT_FAIL');\n      }\n    }).catch(() => {\n      router.quarantine(id, 'HEARTBEAT_TIMEOUT');\n    });\n  }\n}, 30000);\n```\n\n## Anti-Fake-Pass Checklist\n\n- [ ] QUORUM value ≥ 3 — never use `QUORUM = 1` even temporarily\n- [ ] Quarantined agents excluded from voter pool\n- [ ] Stale agents (heartbeat > TTL) excluded from voter pool\n- [ ] Dual-verify divergence investigated — not silently retried\n- [ ] Vote results logged to Merkle audit chain with fingerprints\n",{"name":5,"origin":24,"license":15,"version":25,"description":7,"compatibility":26},"PBFT (Castro & Liskov 1999), Raft (Ongaro & Ousterhout 2014), YAMTAM rule 54","1.0.0","claude-sonnet-4-6, claude-opus-4-7","main","481dcd7dd2e288b9d627a2bd017db70e64e6c6fa",".claude\u002Fskills\u002Fbft-consensus-patterns",2,"https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI","https:\u002F\u002Fyana.vutam.link\u002F","https:\u002F\u002Fgithub.com\u002FHoronomos-laps","https:\u002F\u002Fyana.vutam.link","An open-source governed runtime & execution environment for multi-agent AI systems.","2026-11-14 13:24:09",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add Horonomos-laps\u002FYana-AI --skill bft-consensus-patterns",{"tool":43,"command":44},"bunx","bunx skills add Horonomos-laps\u002FYana-AI --skill bft-consensus-patterns",{"tool":46,"command":47},"pnpm","pnpm dlx skills add Horonomos-laps\u002FYana-AI --skill bft-consensus-patterns","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fbft-consensus-patterns\u002FSKILL.md",true,[],[52,60,67,75,83,91],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":56,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M735GKET5YVYKAY62W2P5YXB","openai--sentry--sentry","Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.","MIT","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fopenai--sentry--sentry\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M73DCAP83T17HY7SMGK7MGFE","ito-basket-compare","Compare Itô prediction-market baskets against a user's knowledge base, portfolio notes, financial context, watchlist, or research thesis. Use for read-only basket comparison and gap analysis without investment advice or live trading.","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fito-basket-compare\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":71,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M734CYEMZFDR3KH6SW0JP8TD","implementing-network-traffic-baselining","Build network traffic baselines from NetFlow\u002FIPFIX data using Python pandas for statistical analysis, z-score anomaly detection, and hourly\u002Fdaily traffic pattern profiling","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":79,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M73ASZ6NJRJM44Z2P84NGQ3Q","detecting-evasion-techniques-in-endpoint-logs","Detects defense evasion techniques used by adversaries in endpoint logs including log tampering, timestomping, process injection, and security tool disabling. Use when investigating suspicious endpoint behavior, building detection rules for evasion tactics, or conducting threat hunting for stealthy adversary activity. Activates for requests involving evasion detection, defense evasion analysis, log tampering detection, or MITRE ATT&CK TA0005.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":87,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M734AFNXD06Z78QRK0VKGT7Q","implementing-microsegmentation-with-guardicore","Implementing microsegmentation using Akamai Guardicore Segmentation to map application dependencies, create granular network policies, visualize east-west traffic flows, and enforce least-privilege communication between workloads across data centers and cloud.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M736TK27QMCXK0DVCH25SJN5","ramdisk-tmpfs-patterns","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Framdisk-tmpfs-patterns\u002FSKILL.md",[],[]]