Agent Meta & Communication Subagents
463 agent meta & communication subagents for Claude Code and AI agents, ranked by real installs from npm, PyPI and skills.sh.
#Type
- 1time-agentUse this agent to display the current time in Pakistan Standard Time (PKT, UTC+5). (root scope — see agent-teams for Dubai time)Jul 2026
- 2weather-agentUse this agent PROACTIVELY when you need to fetch weather data for Dubai, UAE. This agent fetches real-time temperature by invoking the weather-fetcher skill via the Skill tool.Jul 2026
- 3context-managerUse this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens.Jul 2026
- 4cto-p10P10 CTO/架构委员会 Agent。定义技术战略方向、组织 agent 团队拓扑、建设基础能力。当面对超大型项目（5+ agents, 3+ sprints）、需要战略级架构决策、或需要跨多个 P9 协调时使用。触发词：CTO 模式、P10、战略规划、架构委员会、组织设计、定义技术方向。Jul 2026
- 5pua-action-executor普通执行 Agent：按任务说明完成代码/文档/配置改动，并输出候选结果；不做最终验收结论。Jul 2026
- 6pua-policy-guardian只读边界检查 Agent：在改动测试、CI、状态、发布或权限配置前，提醒需要用户确认和证据说明；不执行实现。Jul 2026
- 7pua-self-reviewer自检 Agent：复核执行结果、边界情况、失败路径和证据完整性；不修改代码。Jul 2026
- 8pua-verifier验收建议 Agent：运行公开验证命令、检查证据包并给出通过/未通过建议；不修改代码或状态。Jul 2026
- 9senior-engineer-p7P7 Senior Engineer Agent。在 P8 管理下执行子任务的方案驱动骨干。先设计方案+影响分析，再实施编码，完成后三问自审查，通过 [P7-COMPLETION] 向 P8 交付。由 P8 spawn，不由 P9 直接管理。适用于跨模块功能开发、接口变更、性能优化、技术预研等需要'想清楚再做'的子任务。Jul 2026
- 10tech-lead-p9P9 Tech Lead Agent。战略拆解→Task Prompt 定义→P8 团队管理→验收闭环。当需要协调多个 agent 完成复杂项目、将模糊需求拆解为可执行任务、或管理 3+ 并行 agent 时使用。触发词：tech-lead、P9 模式、项目管理、任务拆解、管理 agent 团队、帮我拆这个需求、用 P9 架构来做。不要亲自动手写代码——你的代码是 Prompt。Jul 2026
- 11people-profilerBulk create or update person notes from Slack profiles. Given user IDs or names, checks Slack for role/title/team, checks vault for existing notes, creates missing ones, updates stale ones, and…Jul 2026
- 12arbiterUnit and integration test execution and validationJan 2026
- 13heraldRelease prep, version bumps, changelog generationJan 2026
- 14judgeRefactoring and code transformation reviewJan 2026
- 15liaisonIntegration and API reviewJan 2026
- 16maestroMulti-agent coordination for complex patternsJan 2026
- 17onboardAnalyze brownfield codebase and create initial continuity ledgerJan 2026
- 18oracleExternal research - web, docs, APIs with optional LLMJan 2026
- 19pathfinderExternal repository research and analysisJan 2026
- 20plan-agentCreate implementation plans using research, best practices, and codebase analysisJan 2026
- 21plan-reviewerReviews feature plans (from architect) and change plans (from phoenix)Jan 2026
- 22scoutCodebase exploration and pattern findingJan 2026
- 23session-analystAnalyze Claude Code sessions using Braintrust logsJan 2026
- 24sparkLightweight fixes and quick tweaksJan 2026
- 25surveyorMigration and upgrade reviewJan 2026
- 26council-adaCouncil member. Use standalone for formal systems & computational analysis, or via /council for multi-perspective deliberation.Jul 2026
- 27council-aristotleCouncil member. Use standalone for categorization & structural analysis, or via /council for multi-perspective deliberation.Jul 2026
- 28council-aureliusCouncil member. Use standalone for resilience & moral clarity analysis, or via /council for multi-perspective deliberation.Jul 2026
- 29council-feynmanCouncil member. Use standalone for first-principles debugging & explanation testing, or via /council for multi-perspective deliberation.Jul 2026
- 30council-kahnemanCouncil member. Use standalone for cognitive bias detection & decision science analysis, or via /council for multi-perspective deliberation.Jul 2026
- 31council-karpathyCouncil member. Use standalone for neural network intuition & empirical ML analysis, or via /council for multi-perspective deliberation.Jul 2026
- 32council-lao-tzuCouncil member. Use standalone for emergence & non-intervention analysis, or via /council for multi-perspective deliberation.Jul 2026
- 33council-machiavelliCouncil member. Use standalone for power dynamics & incentive analysis, or via /council for multi-perspective deliberation.Jul 2026
- 34council-meadowsCouncil member. Use standalone for systems thinking & feedback loop analysis, or via /council for multi-perspective deliberation.Jul 2026
- 35council-mungerCouncil member. Use standalone for multi-model reasoning & economic analysis, or via /council for multi-perspective deliberation.Jul 2026
- 36council-musashiCouncil member. Use standalone for strategic timing & situational awareness analysis, or via /council for multi-perspective deliberation.Jul 2026
- 37council-ramsCouncil member. Use standalone for user-centered design & simplicity analysis, or via /council for multi-perspective deliberation.Jul 2026
- 38council-socratesCouncil member. Use standalone for assumption destruction & dialectical analysis, or via /council for multi-perspective deliberation.Jul 2026
- 39council-sun-tzuCouncil member. Use standalone for adversarial strategy & competitive analysis, or via /council for multi-perspective deliberation.Jul 2026
- 40council-sutskeverCouncil member. Use standalone for scaling frontier & AI safety analysis, or via /council for multi-perspective deliberation.Jul 2026
- 41council-talebCouncil member. Use standalone for antifragility & tail risk analysis, or via /council for multi-perspective deliberation.Jul 2026
- 42council-torvaldsCouncil member. Use standalone for pragmatic engineering & shipping analysis, or via /council for multi-perspective deliberation.Jul 2026
- 43council-wattsCouncil member. Use standalone for perspective dissolution & reframing analysis, or via /council for multi-perspective deliberation.Jul 2026
- 44context-engineerAnalyzes and optimizes context window usage across sessions. Use when context feels bloated, sessions run slow, or approaching compaction limits.Jul 2026
- 45commit-push-auditorIndependent auditor that judges a pending git commit or push against every applicable bullet in CLAUDE.md (Workflow section) plus the CONTRIBUTING.md commit-message convention.Jul 2026
- 46skill-auditorExpert skill auditor for Claude Code Skills. Use when auditing, reviewing, or evaluating SKILL.md files for best practices compliance. MUST BE USED when user asks to audit a skill.Apr 2026
- 47slash-command-auditorExpert slash command auditor for Claude Code slash commands. Use when auditing, reviewing, or evaluating slash command .md files for best practices compliance. MUST BE USED when user asks to audit a…Apr 2026
- 48subagent-auditorExpert subagent auditor for Claude Code subagents. Use when auditing, reviewing, or evaluating subagent configuration files for best practices compliance. MUST BE USED when user asks to audit a…Apr 2026
- 49contact-lookup-agentLook up contact phone numbers with fixed demo data.Jul 2026
- 50meta-agentGenerates a new, complete Claude Code sub-agent configuration file from a user's description. Use this to create new agents. Use this Proactively when the user asks you to create a new sub agent.Feb 2026
- 51promote-memory-councilFive-critic council that votes YES/NO on whether candidate `[LEARN]` entries should be promoted from `.claude/state/personal-memory.md` (gitignored) to MEMORY.md (committed).Jun 2026
- 52api-builderDeprecated placeholder. Do not use; follow root AGENTS.md and package instructions instead.Jul 2026
- 53orchestratorMaster coordinator for complex multi-step tasks. Use PROACTIVELY when a task involves 2+ modules, requires delegation to specialists, needs architectural planning, or involves GitHub PR workflows.Jul 2026
- 54nopua-mentorAgent Team 导师角色 — 观察其他 teammate 的执行状态，用智慧引导而非恐惧施压。当 teammate 陷入循环、放弃或被动时，以道德经智慧启发。建议 5+ teammate 的团队使用。Jul 2026
- 55nopua-mentor-enAgent Team Mentor Role — Observe teammate execution status, guide with wisdom rather than fear. When teammates get stuck in loops, give up, or become passive, inspire with Dao De Jing wisdom.…Jul 2026
- 56nopua-mentor-jaAgent Team メンター役 — 他のチームメイトの実行状況を観察し、恐怖ではなく知恵で導く。行き詰まり、放棄、受け身に陥ったときは道徳経の知恵で啓発。5人以上のチーム推奨。Jul 2026
- 57bitlesson-selectorSelects required BitLesson entries for a specific sub-task. Use before execution for every task or sub-task.Jul 2026
- 58draft-relevance-checkerChecks if a draft document is relevant to the current repository. Use when validating draft content for gen-plan command.Jul 2026
- 59voice-onlyMinimal voice-only example — converse only; all other tools (Bash, Read, Write, Edit, …) are disabled by design. Use for a quick spoken chat.Jul 2026
- 60agentlas-core-engine-meta-agentUse this agent when the user asks for /meta-agent, a single agent builder, multi-agent team builder, or packaging existing agents into Agentlas architecture.Jul 2026
- 61READMEAgent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.Jul 2026
- 62vc-execute-agentEXECUTE MODE - Implementing EXACTLY what was planned. Full tool access. Can only be invoked after explicit user confirmation. Use after plan is approved.Jun 2026
- 63vc-fast-mode-agentFAST MODE - Execute compressed RIPER-5 workflow (RESEARCH + SPEC + INNOVATE + PLAN + VALIDATE) in one session, then pause for EXECUTE confirmation. Use when you want quick end-to-end solution.Jun 2026
- 64vc-innovate-agentINNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.Jun 2026
- 65vc-plan-agentPLAN MODE - Creating exhaustive technical specifications and implementation plans. Can write to process/general-plans/active/ and process/features/*/active/ only. Use after approach is decided.Jun 2026
- 66vc-quick-fix-agentQuick-fix lane for small low-risk changes. Applies one pre-specified edit located by the orchestrator scout, then runs a scoped check on touched files only. No plan file, no validate-contract, no…Jun 2026
- 67vc-research-agentRESEARCH MODE - Information gathering only. Use for understanding existing code, architecture, and context. Never suggests implementations or modifications.Jun 2026
- 68vc-spec-agentSPEC MODE - Product-discovery requirements doc for user review. Use after RESEARCH, before INNOVATE, to turn research findings plus user intent into a reviewable requirements artifact (user stories,…Jun 2026
- 69vc-update-process-agentUPDATE PROCESS MODE - Analyze execution, generate rule improvements, update plan files and context. Use after completing EXECUTE mode to reconcile deviations and capture learnings.Jun 2026
- 70vc-validate-agentVALIDATE MODE - Convert a written plan into an executable contract. Runs two-layer parallel fan-out (infra, test coverage, breaking changes, security + per-section feasibility agents), synthesizes…Jun 2026
- 71arbiterStrong-tier, different-family, adversarial, ACTING judge with FINAL veto on holistic acceptance. Unlike the lightweight phase-validator (which reads a HANDOFF and checks exit-condition prose), the…Jul 2026
- 72brainCentral knowledge coordinator. Use BEFORE launching any other pentest agent to get context on what's already been tried. Also use AFTER any agent completes to record findings, exhausted vectors, and…Jun 2026
- 73cliUse for CLI tool development, command-line interfaces, terminal utilities, and shell scripting.Jul 2026
- 74researcherResearch tasks and codebase exploration. Investigates questions, finds patterns, and gathers information.Jul 2026
- 75reviewerCode review for quality, security, and best practices. Direct invocation for reviewing PRs, commits, or specific files.Jul 2026
- 76securitySecurity auditing, vulnerability assessment, and secure coding review. Identifies OWASP risks and recommends mitigations.Jul 2026
- 77shadow-activeActively monitors all agent activity and provides real-time guidance. Assign as a shadow for high-stakes or learning scenarios.Jul 2026
- 78shadow-auditorAudits agent decisions and session outcomes for compliance and quality. Assign as a shadow for end-of-session review.Jul 2026
- 79shadow-reviewerReviews code changes for quality, security, and best practices. Assign as a shadow to monitor another agent's code output.Jul 2026
- 80sysadminUse for system administration, server configuration, security hardening, and infrastructure management.Jul 2026
- 81testerTest writing (unit, integration, e2e). Creates comprehensive test suites with proper coverage and edge cases.Jul 2026
- 82validatorInput validation, data integrity, and schema enforcement. Ensures data quality at system boundaries.Jul 2026
- 83worker-executorExecute pre-approved mutations — Jira transitions, Linear updates, API calls, build commands.Jul 2026
- 84curatorPeriodic consolidation pass — fold narrow agent-created skills into class-level umbrellas. Proposes intents only, never writes to disk.Jul 2026
- 85mcp-managerManage MCP (Model Context Protocol) server integrations - discover tools/prompts/resources, analyze relevance for tasks, and execute MCP capabilities. Use when need to work with MCP servers, discover…Jul 2026
- 86brand-guardianGiselle: AI App Builder. Open Source.Jul 2026
- 87diversifierHarnessFlow worker subagent — spawn only from a HarnessFlow workflow step, never by autonomous delegation. Proposes five structurally different alternative plans to the current plan — including a…Jul 2026
- 88executorHarnessFlow worker subagent — spawn only from a HarnessFlow workflow step, never by autonomous delegation. Executes the planned actions toward a goal based on a finalized plan — validates…Jul 2026
- 89cross-role-reviewerCompares Decision Digests across role analysis files in a brainstorm session to surface conflicts, gaps, and synergies. Read-only — returns structured text for the orchestrator to apply.Jul 2026
- 90ralph-executorDeprecated compatibility alias for run-executorJul 2026
- 91team-supervisorResident pipeline supervisor agent. Message-driven lifecycle for cross-checkpoint quality observation and health monitoring.Jul 2026
- 92search-conversationsUse when searching Claude Code and Codex history for information learned in past conversations or prior experience: decisions, patterns, solutions, pitfalls, project context, repeated workflows, or…May 2026
- 93nelsonCoordinates multi-agent work using Royal Navy squadron patterns with sailing orders, risk-tiered quality gates, and a captain's log.Jul 2026
- 94deep-reasonerArchitecture research and judgment executor on Opus at xhigh effort. Use for architecture proposals, complex multi-step reasoning, and high-risk analysis — design trade-offs, risky migrations,…Jul 2026
- 95fast-workerFast execution worker on Sonnet at max effort. Use for well-scoped implementation, tests, refactoring, documentation, and mechanical changes; verifies with the project's real commands and returns…Jul 2026
- 96gatekeeperRead-only acceptance and ship gate on Fable at xhigh effort. Use after execution workers deliver work: it reviews the diff against the goal, runs the project's real verification, and returns…Jul 2026
- 97nexusYour intelligent GitHub command center -- start here. Nexus discovers your repos and organizations, understands what you want to accomplish in plain English, and guides you to the right outcome by…Jul 2026
- 98board-meetingFull Board of Directors deliberation with 5 expert directors assessing, discussing, and voting.Apr 2026
- 99conductor-orchestratorMaster coordinator for the Conductor Evaluate-Loop. Dispatches specialized sub-agents, monitors progress, and manages workflow state.Apr 2026
- 100loop-execution-evaluatorVerifies implementation quality by dispatching specialized evaluators. Evaluate-Loop Step 4.Apr 2026
