Menu
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.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
| name | new-persistent-agent |
| description | 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. |
Create one global, directory-backed TerMinal persistent agent.
Persistent agents live outside repos:
~/.config/TerMinal/persistent-agents/<id>/
Create exactly one new directory with:
agent.jsonINSTRUCTIONS.mdMEMORY.mdSTATE.mdJOURNAL.mdartifacts/agent.json:
{
"id": "kebab-case",
"title": "Short label",
"description": "One-line purpose",
"engine": "claude",
"model": "",
"tags": [],
"createdAt": 1760000000000,
"updatedAt": 1760000000000
}
engine may be claude, codex, or cursor.
INSTRUCTIONS.md: stable operating guidance for this agent.MEMORY.md: durable facts, preferences, decisions, and recurring lessons.STATE.md: current status, open threads, and next actions.JOURNAL.md: append-only run history. Add an initial creation entry.artifacts/: empty directory for future outputs. In INSTRUCTIONS.md, tell
the agent to write human-readable run output to
artifacts/<date-or-run-id>/report.md and optional metadata to
artifacts/<date-or-run-id>/artifact.json.Optional artifact.json shape:
{
"title": "Run analysis",
"kind": "report",
"createdAt": "2026-06-01T12:00:00.000Z",
"runId": "optional",
"summary": "Short display summary",
"primaryPath": "artifacts/<date-or-run-id>/report.md"
}
.agents files for this skill.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 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.
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'.