菜单
spawn parallel amp agents in tmux with thread linkage. use for INDEPENDENT side-quests discovered during main work. NOT for spawning multiple agents to review/evaluate the same thing.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | spawn |
| description | spawn parallel amp agents in tmux with thread linkage. use for INDEPENDENT side-quests discovered during main work. NOT for spawning multiple agents to review/evaluate the same thing. |
spawn amp agents in tmux windows with automatic thread linkage.
before spawning, ask:
spawn parallelizes INDEPENDENT work. don't spawn agents to produce conflicting findings you'll need to reconcile.
short threads outperform long threads. see bundled references:
key insight: agents get drunk on too many tokens. spawning keeps each thread focused on ONE task with minimal context, then links via read_thread.
scripts/spawn-amp "<task description>"
creates a detached tmux window, pipes the task to amp, links to parent thread via $AMP_CURRENT_THREAD_ID, includes callback instructions with $TMUX_PANE. echoes the agent's name.
agents get auto-assigned fairy names from assets/ (e.g., ted_glimmermoss).
AGENT1=$(scripts/spawn-amp "task 1") && AGENT2=$(scripts/spawn-amp "task 2")
tmux select-window -t "$AGENT1" # switch to
tmux capture-pane -p -t "$AGENT1" # check output
tmux kill-window -t "$AGENT1" # stop
tmux list-windows -F '#W' # list all
when context fills up, spawn a successor with full context:
scripts/spawn-amp "HANDOFF: <context summary>. load the coordinate skill for multi-agent work."
for orchestrating multiple agents with bidirectional communication, load the coordinate skill.
Interact with local Chrome browser session (only on explicit user approval after being asked to inspect, debug, or interact with a page open in Chrome)
orchestrate multiple amp agents with bidirectional tmux communication. use for multi-hour autonomous runs with INDEPENDENT parallel tasks. NOT for review courts or generating opinions to reconcile.
systematic investigation and debugging methodology. hypothesis-driven analysis with verification agents. use for incident response, codebase archaeology, dependency mapping, root cause analysis, or any investigation requiring verified findings.
apply documentation philosophy — explain why, not what. use for jsdocs, READMEs, inline comments.
git workflows for agents: ship (stage → commit → push), worktree (parallel branches), hunks (selective staging). never force push, never git add -A, conventional commits. triggers on: commit, push, stage, ship, git add, worktree, hunks, selective staging.
structured investigation-to-PR workflow for linear issues. hypothesis-driven debugging with browser validation and counterfactual proof. use when investigating a linear ticket, fixing a UI bug, or shipping a fix with evidence. triggers on: investigate issue, fix bug, nexus-fix, AXM-, linear issue.