菜单
Create or update a TerMinal agent from a natural-language request — writes a script-first .agents/<id>.sh + <id>.json sidecar. Use on /new-agent, 'create an agent', or wanting a reusable button/scheduled agent.
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 | new-agent |
| description | Create or update a TerMinal agent from a natural-language request — writes a script-first .agents/<id>.sh + <id>.json sidecar. Use on /new-agent, 'create an agent', or wanting a reusable button/scheduled agent. |
Create a repo-local TerMinal agent as a bash script plus JSON sidecar. Agents show up in the TerMinal Agents tab and can be run manually or scheduled.
Default target is the current repo:
.agents/<id>.sh — executable script body (chmod 755).agents/<id>.json — metadata sidecarIf the user explicitly asks for a global agent, write to
~/.config/TerMinal/scripts/<id>.sh and <id>.json instead.
CLAUDE.md / AGENTS.md.agents/scripts.md if present.agents/forge.md if the agent may open a PR/MR.agents/*.sh and .agents/*.json to avoid duplicate idsid, a clear title, a one-line description, and
a lucide icon name.Use this shape:
#!/usr/bin/env bash
set -uo pipefail
repo="${TERMINAL_REPO:-$(git rev-parse --show-toplevel)}"
worktree="${TERMINAL_WORKTREE:-$repo}"
engine="${TERMINAL_ENGINE:-claude}"
# Recurring/report agents should default cheap; implementation agents may leave
# this empty so the selected engine uses its normal coding default.
model="${TERMINAL_MODEL:-haiku}"
# Do deterministic work first. For TerMinal helpers:
# terminal-cli ticket "<title>" "<body>"
# terminal-cli hitl "<title>" "<action>"
# terminal-cli activity <kind> "<title>" "<detail>"
# terminal-cli state get|set <key> [value]
When calling an engine from inside the script:
case "$engine" in
codex) model="${TERMINAL_MODEL:-gpt-5-mini}" ;;
cursor) model="${TERMINAL_MODEL:-composer-2.5-fast}" ;;
*) model="${TERMINAL_MODEL:-haiku}" ;;
esac
claude -p "$prompt" --permission-mode auto ${model:+--model "$model"}
codex exec -s danger-full-access -C "$worktree" ${model:+--model "$model"} "$prompt"
cursor-agent -p --force --trust --workspace "$worktree" ${model:+--model "$model"} "$prompt"
Rules:
tail -200, head -100,
rg -n -C2 ... | head -160). Prefer letting the engine open a specific path
over pasting whole files into the prompt.main/master.terminal-cli ticket for findings the agent should not fix in the same run.terminal-cli hitl only for true human blockers.hitl.json or resolve it from the
script. After filing, exit only if that lane is blocked; otherwise continue
independent work and periodically re-check the blocker or query HITL status.exit 0 for no-op success.{
"id": "kebab-case",
"title": "Short label",
"description": "One-line summary",
"icon": "Bot",
"opensPr": false,
"engine": "claude",
"model": "haiku",
"inPlace": false
}
Set opensPr: true only if the agent is expected to commit and open a PR/MR.
engine may be "claude", "codex", or "cursor"; use the user's selected
engine unless the agent has a clear reason to prefer one. For recurring
report/precheck agents, prefer cheap model defaults (haiku,
composer-2.5-fast, or a small Codex model such as gpt-5-mini). Leave
model empty only for implementation-heavy agents where the engine's coding
default is intentional.
Set inPlace: true only for agents that intentionally mutate the current repo
without a worktree; most agents should leave it false.
End with the created/updated script path, sidecar path, and how to run it from TerMinal.
Run a scheduled cadence agent from an .agents/<kind>.md spec — isolated worktree, SHA-gated no-op on re-runs, then reports findings or proposes a ticket+MR. Use on /check <kind>, a scheduled-agent run, or wiring a launchd schedule.
Delegate a GitHub/GitLab PR review to Codex: a deterministic preflight does recon, then Codex scores six axes into one artifact at .TerMinal/reviews/<pr>/<sha>.md (v2) or .reviews/<pr>/<sha>.md (legacy v1). Use on /code-review or 'review this PR'.
FORCE-MODE hotfix: smallest patch → commit → push DIRECTLY to main → follow-up ticket. Needs TERMINAL_FORCE_MAIN=1 (hook-enforced). Use on /emergency-fix or 'this is breaking prod' / 'hotfix' / 'we need to revert now'.
Continuous autonomous orchestrator — the no-handoff loop around /stacked-mr: reconcile (/merge-sync), build+batch-review a stack to the bar, optionally refill via discovery, repeat. Parks HITL, never merges to main. Use on /factory or 'work the backlog autonomously / continuously'.
Create a global TerMinal persistent memory agent. Use when the user runs /new-persistent-agent or asks for a memory-aware agent that keeps its own INSTRUCTIONS.md, MEMORY.md, STATE.md, JOURNAL.md, and artifacts directory.
Take a backlog ticket from idea to open PR: feature branch → TDD → push → open PR (gh) → link the PR back into the ticket. Does NOT auto-run tests/review. Use on /pr-creation or 'start work on a ticket'.