Results for “subagents”

Run a task iteratively over a user-specified duration by dispatching subagents. The orchestrator stays strictly linear and time-checked, but each iteration fans out MULTIPLE subagents in parallel over independent units (and those subagents may fan out further). Shared state — a compact progress digest and a growing environment cheatsheet — lives on disk and is passed to every subagent BY REFERENCE, killing the per-subagent rediscovery tax. Every subagent first reads an initialiser preamble that points it at that shared state and makes it write findings back, so the cheatsheet populates itself; role prompts are produced ONCE on the filesystem by a single scaffold command and dispatched by path, never re-typed per dispatch. Subagents persist their results to disk and return only a tiny status, so the orchestrator's context stays small and lasts. The orchestrator classifies the goal as FINITE or OPEN-ENDED: finite lists may finish early; open-ended goals use the full duration, never idle, never manufacture busywork. Use when the user gives a task and a duration and wants it ground out iteratively by subagents over that time.

The English summary is being prepared. Showing the original description.

Stack Honey onto Superpowers-style workflows (subagent-driven-development, dispatching-parallel-agents, executing-plans) and any orchestration that dispatches fresh subagents. Dispatched subagents run in isolated context and do NOT inherit the session's Honey hook, so they emit full-fat code and verbose reports. Use when you are about to dispatch implementer/reviewer/fixer/parallel subagents: it gives the exact Honey directive to paste into each dispatch prompt, with a worker variant and a reviewer variant, so the levers apply inside the subagents too — where the multiplied cost actually is.

The English summary is being prepared. Showing the original description.

Chooses how to launch subagents from Claude Code (the Agent tool, a Workflow script, or headless claude -p children) and runs a headless fan-out from one background command. Use for "fan this out to 50 agents", "run these tasks in parallel", "launch subagents for each file", "should I spawn agents or write a workflow", "batch this through Haiku", "run claude -p in parallel", "dispatch a task list without the launches eating my context", or before any launch of more than a handful of subagents, where the launching itself is the cost. Covers the parent-turn cost of each mechanism, concurrency ceilings, what context and tools each child gets, effort control, output contracts, a cost ledger, and resume after interruption.

The English summary is being prepared. Showing the original description.

Protocol that evo optimization subagents follow when dispatched from /optimize. Auto-loaded by spawned subagents via their host's skill loader. The orchestrator may also invoke this skill to understand the brief shape its dispatched subagents expect + what they're required to emit -- useful when writing briefs or debugging a subagent's behavior.

The English summary is being prepared. Showing the original description.

Drive structured autoresearch iteration after evo:discover and the baseline commit. Use when the user invokes /evo:optimize or asks to try ideas, try variants, run experiments, use available GPUs, improve the current best/frontier, continue an evo search, or compare candidate changes in an evo workspace. The orchestrator plans and spawns optimization subagents; candidate edits/runs belong to those subagents. Width is set via subagents=N (1 for serial workloads, larger for parallel); the loop's structural value applies at any width.

The English summary is being prepared. Showing the original description.

Choose, configure, launch, and collect bounded subagents for research and engineering decisions. Root agents and delegation-capable subagents should read this before delegating: every task requires an explicit model tier, and high-leverage work such as research ideation, round planning, plateau pivots, large research reviews, hard optimization, disputed evidence, and expensive experiment portfolios requires frontier judgment.

The English summary is being prepared. Showing the original description.

Guide for defining and using Claude subagents effectively. Use when (1) creating new subagent types, (2) learning how to delegate work to specialized subagents, (3) improving subagent delegation prompts, (4) understanding subagent orchestration patterns, or (5) debugging ineffective subagent usage.

The English summary is being prepared. Showing the original description.

Expert en Claude Code subagents (équipe dev orchestrée, contexte isolé, CLAUDE.md, multi-agent)

The English summary is being prepared. Showing the original description.

Coordinate subagents, separate agents assigned tasks, to pursue a long-running goal in one session. Maintain dialogue with the user while improving working conditions, shared rules, and access to information needed for future tasks.

• Coordinating agents around a long-term goal
• Continuing user dialogue during background work
• Improving shared rules and working conditions

Carry out a phased implementation plan with subagents assigned to implementation, verification, pattern checks, and code review. Each phase must pass verification before changes are committed and pushed, with context prepared for the next phase.

• Execute a plan created with make-plan
• Delegate implementation work by phase
• Verify changes and review code before committing

Execute a written work plan by assigning implementation and verification to subagents. Track progress, isolate work in Git worktrees, record test evidence, and require independent verification before marking tasks complete, with optional pull request delivery.

• Executing a saved work plan
• Assigning independent tasks to parallel agents
• Resuming work with recorded progress and evidence

Research a topic across multiple sources and turn the findings into a readable report. The skill coordinates separate research agents to compare options, examine markets or trends, and synthesize literature into a coherent narrative.

• Comparing products or services
• Researching markets and industry trends
• Reviewing studies on a topic

Design how an AI agent trims long conversations and large tool outputs while retaining decisions, constraints, failed approaches, and sources. Compare summarization strategies, choose compression triggers, and consider separate subagents to keep intermediate information out of the main conversation.

• Managing large search results and tool outputs
• Preserving decisions and constraints during summarization
• Choosing compression triggers and batch processing

Analyze Claude Code session transcripts and create an interactive HTML usage report. Explore token consumption, cache performance, subagents, skills, and costly prompts, with findings and improvement suggestions tied to the actual usage data.

• Reviewing token usage over a chosen period
• Comparing consumption across projects and skills
• Investigating cache performance and breaks

Create, update, explain, and compare Excalidraw diagrams through separate subagents. Keeps lengthy diagram data out of the main conversation, returning concise summaries of components, connections, structural differences, and completed changes.

• Explaining components and connections in an existing diagram
• Adding a component and its connections
• Creating an architecture diagram or flowchart

Give subagents or short sessions a compact set of working rules for checking evidence, changing unsuccessful approaches, and verifying results. It also defines agent roles and uses stern corporate-style commentary to push execution forward.

• Giving subagents a shared set of execution rules
• Adding evidence checks to short working sessions
• Changing approach after repeated failures

Create an Omnigent agent directory using validated templates for configuration and instructions. Choose how the agent runs, then add web search, shell access, external tool connections, or subagents only when the task requires them.

• Creating a minimal Omnigent agent
• Configuring an agent with web search
• Adding shell access or MCP tool connections

Handle small development tasks directly in the current session, such as typo fixes, configuration changes, and minor refactoring. It skips subagents and PLAN.md files for work that can be described briefly and finished quickly.

• Fix a typo
• Make a small configuration change
• Perform a minor refactor or simple addition

Guide for creating AI subagents with isolated context for complex multi-step workflows. Use when users want to create a subagent, specialized agent, verifier, debugger, or orchestrator that requires isolated context and deep specialization. Works with any agent that supports subagent delegation. Triggers on "create subagent", "new agent", "specialized assistant", "create verifier". Do NOT use for Cursor-specific subagents (use cursor-subagent-creator instead).

The English summary is being prepared. Showing the original description.

Creates Cursor-specific AI subagents with isolated context for complex multi-step workflows. Use when creating subagents for Cursor editor specifically, following Cursor's patterns and directories (.cursor/agents/). Triggers on "cursor subagent", "cursor agent". Do NOT use for generic subagent creation outside Cursor (use subagent-creator instead).

The English summary is being prepared. Showing the original description.

Create production-grade agent .md files aligned with the current Anthropic subagent contract. Also validates existing agents against the marketplace compliance rules. Use when building custom subagents, reviewing agent quality, or creating parallel agent architectures for orchestrator skills. Trigger with "/agent-creator", "create an agent", "build a subagent", or "validate my agent". Make sure to use this skill whenever creating agents/*.md files for plugins or standalone use.

The English summary is being prepared. Showing the original description.

Audit hook delivery health from Agent Monitor data — balance PreToolUse vs PostToolUse (a gap means tools that started but never reported back), detect missing Stop/SubagentStop terminators (sessions/subagents that never closed), and check for stale ingestion (no recent events). Use when hooks look unreliable or events seem to be dropping.

The English summary is being prepared. Showing the original description.

Use when the user asks to "optimize CLAUDE.md", "create a new skill", "write a custom agent", "configure hooks", "manage context window", "set up MCP servers", "scaffold a skill package", "analyze token budget", "create subagents", "configure permissions", "set up worktrees", or "integrate Claude Code with editors". Covers Claude Code CLI mastery, skill authoring, context engineering, hooks automation, subagent creation, and development workflow optimization.

The English summary is being prepared. Showing the original description.

Implements GitHub or GitLab issues via parallel subagents with review gates between task batches. Use when resolving multi-step issues end-to-end.

The English summary is being prepared. Showing the original description.