Results for “sub-agent”

Produce a comprehensive prompt that hands off the current session's work to a fresh session for sub-agent-orchestrated execution. Use when the user wants to execute discussed/planned work in a new session, run a job to completion via sub-agents, or generate a portable handoff prompt with per-task verification. Assumes the target session supports sub-agents. Triggers on "subagent-prompt", "give me a prompt to run this in a new session", "hand this off to sub-agents", "execute this with sub-agents".

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

Decompose substantive work into phases, dispatch each phase to a sub-agent, and adjudicate what comes back. Use whenever a request asks for implementation, investigation, a fix, a review, or any change to files — including small ones — and whenever you are about to read source or run a diagnostic yourself instead of handing it off. Also use when a report from a sub-agent needs judging, when a phase needs re-dispatching, or when a user names one instance of a pattern. Does not apply when your own prompt begins "Your ROLE_TYPE is sub-agent." — then follow references/sub-agent-contract.md instead.

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

Delegate complex work through a tree of Claude Code sub-agents. Each level uses its own working context and returns concise summaries, helping the coordinating agent manage research, verification, and synthesis without retaining every intermediate detail.

• Divide research, expansion, verification, and synthesis into layers
• Handle work with more intermediate detail than one agent can retain
• Assign specialized checks to different leaf agents

Configure tools and skills for sub-agents before dispatching development tasks. Role presets cover implementation, planning, reviews, testing, and verification, with defined boundaries for what each agent should do and whether it may modify files.

• Setting tool permissions before spawning a sub-agent
• Separating implementation, planning, and review roles
• Configuring agents for review without file changes

Autonomous sub-agent hand-off for a fiddly, fully-specified exploit-compile / escalation RUN - the main agent stays on strategy and the board while a cheap sub-agent runs an exact copy-paste checklist behind a false-root/hostname guardrail. Use for "delegate", "offload", "hand this to a sub-agent", "spin a haiku", or the moment a foothold plus a working escalation vector is identified. Main agent dispatches, waits (no parallel duplicate), integrates the result.

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

Cloudflare platform management via Wrangler CLI, Agents SDK (v0.13+), and Browser Rendering API. Deploy Pages, Workers, KV, R2, D1, Queues, Vectorize, Workflows, Hyperdrive. Build stateful AI agents with the full SDK stack — Agent, AIChatAgent, Think, Voice, sub-agents, fibers, HITL, scheduling, observability, Code Mode (Dynamic Worker sandboxes). Budget web scraping via cf_browser.py. Use when deploying to Cloudflare, managing CF infrastructure, configuring wrangler.toml/wrangler.jsonc, building AI agents or chat agents on Workers, adding voice, orchestrating sub-agents, or for cheap web scraping. Triggers: Cloudflare, wrangler, Pages, KV, R2, D1, Workers, Vectorize, Queues, Workflows, Hyperdrive, cf_browser, Browser Rendering, Agents SDK, Code Mode, codemode, MCP, Think, AIChatAgent, Voice agent, sub-agents, fibers, HITL, Dynamic Workers.

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

Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks

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

Analyze Claude Code and Codex usage logs to identify spending drivers, including cache usage, model choices, reasoning, and long sessions. Receive evidence-backed recommendations and hypothetical savings estimates to help decide which changes to try.

• Investigating unexpectedly high agent costs
• Reviewing cache usage
• Reconsidering models used by sub-agents

Coordinate GitHub pull request reviews by assigning comment triage and code changes to dedicated sub-agents. Repeat the process, track decisions and progress, and reply to and resolve threads as fixes are completed.

• Work through outstanding pull request review comments
• Separate required fixes from items outside the pull request scope
• Repeat review and implementation until actionable items are cleared

Split multi-step coding, research, or testing into focused assignments for sub-agents, which are agents handling specific parts of a task. The parent agent retains design decisions, integration, and final verification while independent work runs in parallel.

• Exploring separate groups of files in parallel
• Assigning code changes with clear file ownership
• Running focused tests alongside other work

Review agent work histories to identify recurring failures, repeated discoveries, and stalled tasks. Improve the prompts, specialist agents, skills, tools, and memory that guide future work, then submit those changes separately for review.

• Addressing recurring command or tool failures
• Recording findings that agents repeatedly rediscover
• Turning repeated procedures into skills or tools

Split debugging, audits, searches, and code questions into read-only tasks for sub-agents. Combine their structured reports into an evidence-based answer, requesting follow-up investigations when findings conflict or leave important gaps.

• Investigating a bug without changing code
• Understanding repository structure and design
• Comparing architectures from multiple perspectives

Create and configure Claude Code sub-agents with custom prompts, tools, and models

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

Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and mandatory self-critique verification

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

Reusable approval-loop pattern for fanning out lead personalization across parallel Claude Code Task sub-agents. Shows the user 1 sample personalization, collects feedback, runs 10 more, approves, runs 10 more — stops when 2 consecutive rounds have zero edits, then scales to the full list. ALWAYS uses Claude Code Task tool sub-agents — never an external Anthropic/OpenAI API key. Use when any skill needs per-lead custom variables (situation lines, value lines, CTAs).

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

Manage capa CLI configuration — `capabilities.yaml` / `capabilities.json`, skills, MCP servers, tools, hooks, sub-agents, rules, plugins, AGENTS.md / CLAUDE.md, security options, tool exposure modes, `capa wrap` shadow workspaces, `--passthrough` native writes, registries (including Claude marketplaces), activity traces, and the local Web UI. Use whenever the user edits the capabilities file, runs any `capa` command (init, install, add, wrap, clean, sh, start/stop/restart/status, auth, upgrade, cache, registry), wires up an MCP server, adds a skill from GitHub / GitLab / a registry / a remote URL / a local path, configures secrets via `${VarName}` placeholders, installs lifecycle hooks, defines sub-agents, or troubleshoots a failed install. Use even when the user only names a fragment ("add a skill", "wire up brave search", "wrap cursor", "block this phrase in skills") without saying "capa" — if a `capabilities.yaml` or `capabilities.json` lives at the project root, this is almost certainly the right skill. If the project does NOT yet have a capabilities file, point at the `bootstrap` skill instead.

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

Create and configure Claude Code sub-agents with custom prompts, tools, and models

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

Run Codex CLI, Claude Code, or other coding agents as background processes for programmatic control. Use when a user asks to run a coding agent, delegate a task to another AI, spawn a sub-agent, run Claude Code in the background, or orchestrate multiple coding agents on separate tasks.

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

Delegate coding, code review, analysis, and research jobs to Google Antigravity CLI (agy) sub-agents that run alongside your own work. Use this whenever the user asks to spin off, offload, or delegate a task to Antigravity, agy, Gemini, or an "external agent"; wants a second opinion or independent review from a different model; wants intensive repo work (audits, large refactors, research sweeps) run in the background while you keep working; or says things like "have Antigravity do it", "spin up a sub-agent for this", or "get more done in parallel". Also use it proactively when a task is a good fit for parallel delegation and the user has expressed a preference for using Antigravity workers.

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

Decompose a task into safe parallel sub-agent slices with explicit ownership, optional worktree isolation, per-worker plans, verification, and orchestrator-led integration. Use when the user explicitly asks for delegation, sub-agents, or parallel work and the task can be split into non-overlapping scopes.

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

This skill should be used when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents. Provides scientific delegation framework ensuring world-building context (WHERE, WHAT, WHY) while preserving agent autonomy in implementation decisions (HOW). Use when planning task delegation, structuring sub-agent prompts, or coordinating multi-agent workflows.

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

This skill should be used when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents. Provides scientific delegation framework ensuring world-building context (WHERE, WHAT, WHY) while preserving agent autonomy in implementation decisions (HOW). Use when planning task delegation, structuring sub-agent prompts, or coordinating multi-agent workflows.

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

Terminal session manager for AI coding agents. Use when user mentions "agent-deck", "session", "sub-agent", "MCP attach", or needs to (1) create/start/stop/restart/fork sessions, (2) attach/detach MCPs, (3) manage groups/profiles, (4) get session output, (5) configure agent-deck, (6) troubleshoot issues, or (7) launch sub-agents. Covers CLI commands, TUI shortcuts, config.toml options, and automation.

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

Runtime router for context decisions during a task — decide read-more / stop / ask / assume / delegate, pick a minimal read-set, and time compaction. Front-page mental model is Write / Select / Compress / Isolate; a lazy pattern index routes to 25 context-engineering patterns, one reference per decision. Use when context is near budget, a long session is degrading, you must choose what to read for a task, or you are deciding /compact vs /clear vs a sub-agent. NOT for structural .claude/ overhead audits (see mk:context-audit); NOT for owning persistence (see mk:memory); NOT for USD cost (see mk:budget).

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