{"id":"f47463c5-0ea2-464f-aedd-3065dff6f7b6","entityType":"agent","slug":"ktaletsk-council","name":"council","canonicalUrl":"https://xpersona.co/agent/ktaletsk-council","canonicalPath":"/agent/ktaletsk-council","generatedAt":"2026-04-17T06:15:27.942Z","source":"GITHUB_OPENCLEW","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"description":"Run parallel code reviews with multiple AI agents, then synthesize into one report. Triggers on \"review code\" or \"council review\". --- name: council description: Run parallel code reviews with multiple AI agents, then synthesize into one report. Triggers on \"review code\" or \"council review\". --- Council Code Review Skill This skill runs the same code review prompt against multiple AI agents in parallel, then synthesizes their findings into a single comprehensive report. It supports **Claude Code**, **Codex CLI**, **OpenCode**, and **Cursor** as","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.","installCommand":"git clone https://github.com/ktaletsk/multi-agent-code-review-skill.git","sourceUrl":"https://github.com/ktaletsk/multi-agent-code-review-skill","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/ktaletsk/multi-agent-code-review-skill","kind":"source"}],"safetyScore":94,"overallRank":31.3,"popularityScore":0,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Run parallel code reviews with multiple AI agents, then synthesize into one report. Triggers on \"review code\" or \"council review\". --- name: council description"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[{"label":"be","status":"self-declared"},{"label":"customize","status":"self-declared"}],"verifiedCount":0,"selfDeclaredCount":3,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"},{"key":"be","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"},{"key":"customize","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile capability:be|supported|profile capability:customize|supported|profile"}},"adoption":{"evidence":{"source":"no-adoption-signals","verified":false,"confidence":"low","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":"No source adoption metrics were available."},"stars":0,"forks":0,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":null},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-04-14T22:26:04.190Z","emptyReason":null},"lastUpdatedAt":"2026-04-15T05:21:22.124Z","lastCrawledAt":"2026-04-14T22:26:04.190Z","lastIndexedAt":null,"nextCrawlAt":"2026-04-15T22:26:04.190Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"GITHUB OPENCLEW","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"git clone https://github.com/ktaletsk/multi-agent-code-review-skill.git","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://xpersona.co/api/v1/agents/ktaletsk-council/snapshot","contractUrl":"https://xpersona.co/api/v1/agents/ktaletsk-council/contract","trustUrl":"https://xpersona.co/api/v1/agents/ktaletsk-council/trust"},"curlExamples":["curl -s \"https://xpersona.co/api/v1/agents/ktaletsk-council/snapshot\"","curl -s \"https://xpersona.co/api/v1/agents/ktaletsk-council/contract\"","curl -s \"https://xpersona.co/api/v1/agents/ktaletsk-council/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"GITHUB_OPENCLEW","generatedAt":"2026-04-17T06:15:27.942Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://xpersona.co/api/v1/agents/ktaletsk-council/dossier","snapshotUrl":"https://xpersona.co/api/v1/agents/ktaletsk-council/snapshot","contractUrl":"https://xpersona.co/api/v1/agents/ktaletsk-council/contract","trustUrl":"https://xpersona.co/api/v1/agents/ktaletsk-council/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"GITHUB OPENCLEW","verified":false,"confidence":"high","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"readme":"---\nname: council\ndescription: Run parallel code reviews with multiple AI agents, then synthesize into one report. Triggers on \"review code\" or \"council review\".\n---\n\n# Council Code Review Skill\n\nThis skill runs the same code review prompt against multiple AI agents in parallel, then synthesizes their findings into a single comprehensive report. It supports **Claude Code**, **Codex CLI**, **OpenCode**, and **Cursor** as agent backends -- and you can mix them freely.\n\n## When to Use\n\nActivate this skill when the user asks to:\n- \"Review my code\"\n- \"Run a code review\"\n- \"Review the staged changes\"\n- \"Do a council review\"\n- \"Get multiple perspectives on this code\"\n\n## CRITICAL: Target Directory\n\n**You must pass the USER'S PROJECT DIRECTORY as an argument to the script.**\n\nThe user's project directory is where they started their Claude Code session - NOT this skill's directory. Look for the git repository path in the conversation context (e.g., `/Users/.../git/jupyter_server`).\n\n## Workflow\n\n### Step 1: Identify the Target Repository\n\nDetermine the user's project directory from the conversation context. This is typically shown at the start of the session or can be found by checking where CLAUDE.md is located. It is NOT `/Users/.../skills/council/`.\n\n### Step 2: Run Parallel Reviews\n\nRun the review script and **pass the user's project directory as an argument**:\n\n```bash\n~/.claude/skills/council/scripts/run-reviews.sh /path/to/users/project\n```\n\nFor example, if the user is working in `/Users/ktaletskiy/git/jupyter_server`:\n```bash\n~/.claude/skills/council/scripts/run-reviews.sh /Users/ktaletskiy/git/jupyter_server\n```\n\n**IMPORTANT**: Always pass the full path to the user's project as the first argument.\n\nThe script reads `config.yaml` from the skill directory to determine which agents to run. Each agent entry specifies its own **backend** and **model**, so you can mix and match freely across all four supported backends.\n\nThis will:\n- Run all configured agents in parallel, each via its own backend\n- Save individual JSON results to `<project>/.reviews/`\n- Take 1-3 minutes depending on code size\n\n### Step 3: Synthesize Results\n\nAfter the script completes, read all JSON files from `<project>/.reviews/` (in the user's project directory) and synthesize them into a combined report.\n\n**Synthesis Rules:**\n1. Do NOT mention which agent found which issue\n2. Deduplicate similar issues (same file + same line + same problem = one entry)\n3. If reviewers disagree on severity, use the higher severity\n4. Preserve unique findings from each reviewer\n5. Present findings as if from a single thorough review\n\n**Output Format:**\n\nWrite the combined report to `<project>/.reviews/COMBINED_REVIEW.md` using this structure:\n\n```markdown\n# Code Review Report\n\n**Repository:** [repo name from user's directory]\n**Date:** [today's date]\n\n---\n\n## Summary\n\n[1-2 paragraph summary]\n\n**Consensus:** [X of Y reviewers recommended changes / approved]\n\n---\n\n## Critical Issues (Require Action)\n\n### 1. [Issue Title]\n**Severity:** 🔴 HIGH\n**File:** `path/to/file` (line X)\n\n[Description]\n\n**Recommendation:** [How to fix]\n\n---\n\n## Medium Issues (Should Address)\n\n[Same format, 🟠 MEDIUM]\n\n## Low Issues (Consider Addressing)\n\n[Same format, 🟡 LOW]\n\n## Suggested Improvements\n\n[Numbered list]\n\n---\n\n## Verdict\n\n**[🔴 REQUEST CHANGES / 🟢 APPROVE]**\n\n[Priority action items table]\n```\n\n### Step 4: Report to User\n\nAfter writing the combined report, summarize the key findings:\n- Total issues found (by severity)\n- Top 3 priority items to address\n- Overall verdict\n\n## Configuration\n\nAll configuration lives in `~/.claude/skills/council/config.yaml`:\n\n```yaml\n# Each agent specifies its own backend and model.\n# Mix and match all four backends freely.\nagents:\n  - backend: claude-code\n    model: sonnet\n\n  - backend: codex\n    model: gpt-5-codex\n\n  - backend: opencode\n    model: google/gemini-3-pro\n```\n\n### Backends\n\nEach agent entry requires a `backend` and a `model`:\n\n| Backend | CLI command | `model` format | Requires |\n|---------|-----------|---------------|----------|\n| `claude-code` | `claude -p` | Alias (`sonnet`, `opus`) or full name (`claude-sonnet-4-20250514`) | [Claude Code](https://docs.anthropic.com/en/docs/claude-code) + Anthropic account |\n| `codex` | `codex exec` | Model name (e.g. `gpt-5-codex`) | [Codex CLI](https://github.com/openai/codex) + ChatGPT plan or API key |\n| `opencode` | `opencode run` | `provider/model` (e.g. `anthropic/claude-sonnet-4-20250514`) | [OpenCode CLI](https://opencode.ai) + provider API keys |\n| `cursor` | `cursor-agent` | Model name (e.g. `gemini-3.1-pro`) | [Cursor CLI](https://cursor.com/cli) + subscription |\n\n### Discovering available models\n\n- **Claude Code**: `claude --model` (aliases: `sonnet`, `opus`, `haiku`)\n- **Codex**: `/model` inside `codex` TUI, or see [Codex models docs](https://developers.openai.com/codex/models)\n- **OpenCode**: `opencode models`\n- **Cursor**: `cursor-agent --list-models`\n\n### Other customization\n\n- **Review focus**: Edit `~/.claude/skills/council/prompts/review-prompt.md`\n- **Thinking depth**: Add \"think hard\" or \"ultrathink\" to the prompt\n\n## Files\n\n```\n~/.claude/skills/council/\n├── SKILL.md              # This file\n├── config.yaml           # Backend and model configuration\n├── scripts/\n│   └── run-reviews.sh    # Parallel review runner\n└── prompts/\n    └── review-prompt.md  # Review prompt template\n\n# Output is saved to the user's project:\n<project>/.reviews/\n├── review_*.json         # Individual agent outputs\n└── COMBINED_REVIEW.md    # Synthesized report\n```\n","readmeExcerpt":"--- name: council description: Run parallel code reviews with multiple AI agents, then synthesize into one report. Triggers on \"review code\" or \"council review\". --- Council Code Review Skill This skill runs the same code review prompt against multiple AI agents in parallel, then synthesizes their findings into a single comprehensive report. It supports **Claude Code**, **Codex CLI**, **OpenCode**, and **Cursor** as ","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"~/.claude/skills/council/scripts/run-reviews.sh /path/to/users/project"},{"language":"bash","snippet":"~/.claude/skills/council/scripts/run-reviews.sh /Users/ktaletskiy/git/jupyter_server"},{"language":"markdown","snippet":"# Code Review Report\n\n**Repository:** [repo name from user's directory]\n**Date:** [today's date]\n\n---\n\n## Summary\n\n[1-2 paragraph summary]\n\n**Consensus:** [X of Y reviewers recommended changes / approved]\n\n---\n\n## Critical Issues (Require Action)\n\n### 1. [Issue Title]\n**Severity:** 🔴 HIGH\n**File:** `path/to/file` (line X)\n\n[Description]\n\n**Recommendation:** [How to fix]\n\n---\n\n## Medium Issues (Should Address)\n\n[Same format, 🟠 MEDIUM]\n\n## Low Issues (Consider Addressing)\n\n[Same format, 🟡 LOW]\n\n## Suggested Improvements\n\n[Numbered list]\n\n---\n\n## Verdict\n\n**[🔴 REQUEST CHANGES / 🟢 APPROVE]**\n\n[Priority action items table]"},{"language":"yaml","snippet":"# Each agent specifies its own backend and model.\n# Mix and match all four backends freely.\nagents:\n  - backend: claude-code\n    model: sonnet\n\n  - backend: codex\n    model: gpt-5-codex\n\n  - backend: opencode\n    model: google/gemini-3-pro"},{"language":"text","snippet":"~/.claude/skills/council/\n├── SKILL.md              # This file\n├── config.yaml           # Backend and model configuration\n├── scripts/\n│   └── run-reviews.sh    # Parallel review runner\n└── prompts/\n    └── review-prompt.md  # Review prompt template\n\n# Output is saved to the user's project:\n<project>/.reviews/\n├── review_*.json         # Individual agent outputs\n└── COMBINED_REVIEW.md    # Synthesized report"}],"parameters":{},"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["typescript"],"docsSourceLabel":"GITHUB OPENCLEW","editorialOverview":"Run parallel code reviews with multiple AI agents, then synthesize into one report. Triggers on \"review code\" or \"council review\". --- name: council description: Run parallel code reviews with multiple AI agents, then synthesize into one report. Triggers on \"review code\" or \"council review\". --- Council Code Review Skill This skill runs the same code review prompt against multiple AI agents in parallel, then synthesizes their findings into a single comprehensive report. It supports **Claude Code**, **Codex CLI**, **OpenCode**, and **Cursor** as","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":369,"uniquenessScore":65,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-04-17T06:15:27.942Z","emptyReason":null},"items":[{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-10T18:48:31.762Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/github_openclew","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}