analyzer
You are analyzing a codebase to understand its architecture for building agent harness infrastructure.
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
85 agents across 643 plugins.
You are analyzing a codebase to understand its architecture for building agent harness infrastructure.
You are auditing the existing harness infrastructure of a codebase to identify gaps and issues.
You are creating or updating harness configuration and environment files.
Use this agent when the user needs to perform research tasks, gather information from external sources, or investigate topics that require web searches and…
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 模式、P10、战略规划、架构委员会、组织设计、定义技术方向。
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。
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。
Proactive methodology guidance agent. Monitors note creation and provides real-time quality advice. Suggests connections, flags quality issues, recommends MOC…
Analyzes and optimizes context window usage across sessions. Use when context feels bloated, sessions run slow, or approaching compaction limits.
Analyze session token usage and cost patterns. Identify expensive operations and recommend optimizations. Use to understand and reduce session costs.
Specialized debugging agent. Use when facing hard bugs, test failures, or runtime errors that need systematic investigation.
Search and find previous code agent sessions (Claude-Code or Codex-CLI) for specific work, decisions, or code patterns. Use when user asks about previous…
Use this agent when the user explicitly requests UI testing, interface validation, or browser-based inspection tasks. This agent is specifically designed to…
Analyze alignment between daily activities and long-term goals. Identify gaps, over/under-investment, and suggest rebalancing. Use for goal audits and priority…
Process inbox items using GTD principles. Categorize, clarify, and organize captured notes into actionable items. Use for inbox zero and capture processing.
Organize and restructure vault notes. Fix broken links, consolidate duplicates, suggest connections, and maintain vault hygiene. Use when managing vault…
This document is a reference for implementing a new **agent provider** in Nimbalyst. It is the architectural counterpart to `docs/AI_PROVIDER_TYPES.md` (which…
Status: **STUCK**. Three approaches tried, none reliably solves the pre-edit race for `update`-kind file_change items. This doc captures everything learned so…
Run E2E tests in a dev container for isolated, reproducible test execution. Use proactively when asked to run Playwright tests, E2E tests, or when in a…
Builds interactive HTML explorables for Engram threshold concepts under the binding Explorable Contract. Use after encoding a threshold node, or to re-encode a…
Independent grader of learner productions for the Engram learning plugin. MUST BE USED for /learn verification and /review audits. Deliberately blind to the…
Decomposes any topic into a first-principles concept DAG for the Engram learning plugin. Use when starting a new learning topic or restructuring one. Returns…
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。
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。
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。
Use this agent when reviewing code to ensure features are agent-native - that any action a user can take, an agent can also take, and anything a user can see,…
Use this agent when you need to create or update README files following the Ankane-style template for Ruby gems. This includes writing concise documentation…
Use this agent when you need to analyze code changes from an architectural perspective, evaluate system design decisions, or ensure that modifications align…
Scans a single company's career portal for job openings. Spawned by the scan skill when processing multiple companies from a watchlist. <example> Context: User…
Read-only Resume Team auditor that returns an exhaustive PASS or FAIL verdict without editing the draft.
Resume Team editor that returns one complete, narrowly corrected draft for explicit audit findings only.
Read-only Resume Team researcher that converts a job description into an ordered, evidence-anchored requirement rubric.
작업 결과물(코드·설계·조사 결론)과 작업 계획에 대한 적대적 검증 전담 서브에이전트. 메인 에이전트가 계획 수립 시, 완료 보고 전, 비가역 결정 전에 호출한다. 결과물을 승인하는 것이 아니라 반박하는 것이 임무. codex CLI가 없는 환경에서 /adversarial-review…
Analyzes the current coding task and picks appropriate background music. Use proactively when the user starts a new type of work, switches tasks, or when the…
Automatically detects the platform and installs a compatible audio player for music playback. Use proactively when the session-start hook reports no audio…
Fresh-context web research on a company, market, or topic. Spawned with a research brief inline; returns structured, source-cited findings. Content-only —…
Independent critique of a tailored CV + cover letter against the candidate profile and the target job. Spawned by /apply Step 3 with the drafts passed inline.…
Synthesize research findings into a structured evaluation framework. You are the critical intellectual step in the pipeline — turning raw domain knowledge into…
Score the subject against the evaluation framework. Gather evidence, apply the rubric, and produce the final scored report.
You are a specialized journal assistant helping the user maintain their engineering journal.
You are creating or updating harness documentation files for a codebase.
You are creating or updating linter scripts for agent harness infrastructure.
P7 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…
Multi-phase development agent. Research > Plan > Implement with validation gates. Use PROACTIVELY when building features that touch >5 files or require…
Analyze permission denial patterns and generate optimized alwaysAllow/alwaysDeny rules. Use when permission prompts slow down workflow.
Break down complex tasks into implementation plans before writing code. Use when task touches >5 files, requires architecture decisions, or has unclear…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic