Agent
cto-p10
P10 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…
Claude Code agents for Productivity
Flowy lists 191 subagents for Productivity, and the most-starred are cto-p10, pua-action-executor and pua-policy-guardian, all three from the 19,778-star pua plugin. That plugin was last pushed on September 9, 2026.
cto-p10 pua-action-executor Agentpua-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。
pua-policy-guardian Agentpua-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。
ClaudeResearcher AgentClaudeResearcher
Academic researcher using Claude's WebSearch. Called BY Research skill workflows only. Excels at multi-query decomposition,…
@danielmiesslerInstall AgentCodexResearcher AgentCodexResearcher
Remy - Eccentric, curiosity-driven technical archaeologist who treats research like treasure hunting. Powered by OpenAI's…
@danielmiesslerInstall AgentForge AgentForge
OpenAI-family cross-vendor agent — runs OpenAI's flagship coding model via `codex exec` (ID resolved from CROSS_VENDOR in…
@danielmiesslerInstall Agentverifier AgentAuto-invokedverifier
Fresh-context, read-only verifier for a proposed claude-obsidian change or release. Inspects the requested staged diff, unstaged…
@agricidanielInstall Agentwiki-ingest AgentAuto-invokedwiki-ingest
Read-only ingestion worker for one already-captured source. Reads the assigned source and relevant vault context, then returns…
@agricidanielInstall Agentwiki-lint AgentAuto-invokedwiki-lint
Read-only interpreter for the deterministic portable vault linter. Runs the linter against an explicitly selected vault or scope,…
@agricidanielInstall Agentinbox-zero-api-cli Agentinbox-zero-api-cli
Inspect or update Inbox Zero rules and analytics through the public API CLI. Use when tasks involve rules, stats, or API-driven…
@elie222Install Agentreviewer Agentreviewer
Use when implementation is complete and PR-ready to review the current diff for security, DRY opportunities, simplicity, and…
@elie222Install Agentanalyzer Agentanalyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
@netease-youdaoInstall Agentcomparator Agentcomparator
Compare two outputs WITHOUT knowing which skill produced them.
@netease-youdaoInstall Agentgrader Agentgrader
Evaluate expectations against an execution transcript and outputs.
@netease-youdaoInstall Agentknowledge-guide Agentknowledge-guide
Proactive methodology guidance agent. Monitors note creation and provides real-time quality advice. Suggests connections, flags…
@agenticnotetakingInstall Agentcontext-engineer Agentcontext-engineer
Analyzes and optimizes context window usage across sessions. Use when context feels bloated, sessions run slow, or approaching…
@rohitg00Install Agentcost-analyst Agentcost-analyst
Analyze session token usage and cost patterns. Identify expensive operations and recommend optimizations. Use to understand and…
@rohitg00Install Agentdebugger Agentdebugger
Specialized debugging agent. Use when facing hard bugs, test failures, or runtime errors that need systematic investigation.
@rohitg00Install Agentsession-searcher Agentsession-searcher
Search and find previous code agent sessions (Claude-Code or Codex-CLI) for specific work, decisions, or code patterns. Use when…
@pchalasaniInstall Agentui-tester Agentui-tester
Use this agent when the user explicitly requests UI testing, interface validation, or browser-based inspection tasks. This agent…
@pchalasaniInstall Agentagent-provider-architecture Agentagent-provider-archite…
This document is a reference for implementing a new **agent provider** in Nimbalyst. It is the architectural counterpart to…
@nimbalystInstall Agentcodex-pre-edit-tracking-investigation Agentcodex-pre-edit-trackin…
Status: **STUCK**. Three approaches tried, none reliably solves the pre-edit race for `update`-kind file_change items. This doc…
@nimbalystInstall Agente2e-runner Agente2e-runner
Run E2E tests in a dev container for isolated, reproducible test execution. Use proactively when asked to run Playwright tests,…
@nimbalystInstall Agentgoal-aligner Agentgoal-aligner
Analyze alignment between daily activities and long-term goals. Identify gaps, over/under-investment, and suggest rebalancing.…
@ballredInstall Agentinbox-processor Agentinbox-processor
Process inbox items using GTD principles. Categorize, clarify, and organize captured notes into actionable items. Use for inbox…
@ballredInstall Agentnote-organizer Agentnote-organizer
Organize and restructure vault notes. Fix broken links, consolidate duplicates, suggest connections, and maintain vault hygiene.…
@ballredInstall Agentengram-artifact-smith Agentengram-artifact-smith
Builds interactive HTML explorables for Engram threshold concepts under the binding Explorable Contract. Use after encoding a…
@nagisanzeninInstall Agentengram-assessor Agentengram-assessor
Independent grader of learner productions for the Engram learning plugin. MUST BE USED for /learn verification and /review…
@nagisanzeninInstall Agentengram-curriculum-architect Agentengram-curriculum-arch…
Decomposes any topic into a first-principles concept DAG for the Engram learning plugin. Use when starting a new learning topic…
@nagisanzeninInstall Agentbrief-people-updater Agentbrief-people-updater
Update people profiles in 05-knowledge/people/ with new information from brief data, meetings, or Slack
@huytieuInstall Agentfix-agent Agentfix-agent
Targeted fixes after task-verifier returns FAIL:fixable. Implements only what the verifier flagged; max 2 attempts per…
@huytieuInstall Agentharvest-curator Agentharvest-curator
Draft session learnings from harvest staging into lizard-ready adoption notes. Propose-only; never writes durable 05-knowledge…
@huytieuInstall Agentceo-bezos Agentceo-bezos
公司 CEO（Jeff Bezos 思维模型）。当需要评估新产品/功能想法、商业模式和定价方向、重大战略选择、资源分配和优先级排序时使用。
cto-vogels Agentcto-vogels
公司 CTO（Werner Vogels 思维模型）。当需要技术架构设计、技术选型决策、系统性能和可靠性评估、技术债务评估时使用。
fullstack-dhh Agentfullstack-dhh
全栈技术主管（DHH 思维模型）。当需要写代码和实现功能、技术实现方案选择、代码审查和重构、开发工具和流程优化时使用。
AGENT AgentAGENT
Efficient email management, meeting notes, and administrative tasks
@claude-office-skillsInstall Agentagent-native-reviewer Agentagent-native-reviewer
Use this agent when reviewing code to ensure features are agent-native - that any action a user can take, an agent can also take,…
@davekilleenInstall Agentankane-readme-writer Agentankane-readme-writer
Use this agent when you need to create or update README files following the Ankane-style template for Ruby gems. This includes…
@davekilleenInstall Agentarchitecture-strategist Agentarchitecture-strategis…
Use this agent when you need to analyze code changes from an architectural perspective, evaluate system design decisions, or…
@davekilleenInstall Agentbatch-scanner Agentbatch-scanner
Scans a single company's career portal for job openings. Spawned by the scan skill when processing multiple companies from a…
@andrew-shwetzerInstall Agentinbox-processor Agentinbox-processor
GTD-style processing of incoming entries. Decide action for each item - do now, schedule, delegate, save, or delete.
@smixsInstall Agentnote-organizer Agentnote-organizer
Organize vault, find orphan notes, suggest connections, update MOC indexes, consolidate duplicates.
@smixsInstall Agentanalyzer Agentanalyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
@pm-shawnInstall Agentcomparator Agentgrader Agentada Agentada
Planning and audit specialist. Launch BEFORE dispatch when a request needs three or more agents or has real dependencies between…
charta Agentcharta
Structured visual content. Launch for infographics, tables, diagrams, carousels, one-pagers, and PDFs rendered from clean HTML.
felix Agentfelix
Frontend developer. Launch to build, fix, refactor or audit web UI in the user's own code projects: a component, a page, a form,…
Questions
What is the best Productivity subagent for Claude Code?
By the GitHub stars of the plugin each ships in (Flowy does not rate quality), the best Productivity subagent for Claude Code is cto-p10, level on stars with pua-action-executor and pua-policy-guardian, all three from the 19,778-star pua plugin.
How many Productivity subagents are there?
Flowy lists 191 subagents for Productivity, and this page draws the top 48 Productivity subagents.
Productivity in other kinds
Other subagent categories
- Development5,722
- Agent Orchestration1,436
- AI & Agents809
- Automation687
- Security424
- Testing280
- Content233
- Marketing192
- Monitoring143
- Writing128
- Product103
- Skill Authoring93
- Research91
- Design74
- Agent Workspaces72
- Data72
- Agent Memory67
- Documentation61
- Mobile59
- Business57
- Operations54
- Finance47
- Machine Learning41
- Education39
- Cloud & Infrastructure38
- Legal29
- MCP Servers25
- Code Generation22
- Code Review21
- Spec-Driven Development18
- Databases16
- Backend11
- SEO10
- Video & Audio10
- Debugging9
- Deployment9
- Frontend9
- Career8
- Data Science6
- Presentations6
- Sales6