new-agent

Stars0

Forks0

UpdatedJune 7, 2026 at 22:39

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.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Source

trevormil

trevormil/offline-first-sportsbook

View GitHub Repository View Creator Repositories

Download

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

SKILL.md

readonly

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.

/new-agent — Create a TerMinal 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.

Target files

Default target is the current repo:

.agents/<id>.sh — executable script body (chmod 755)
.agents/<id>.json — metadata sidecar

If the user explicitly asks for a global agent, write to ~/.config/TerMinal/scripts/<id>.sh and <id>.json instead.

Workflow

Read enough local context before writing:
- CLAUDE.md / AGENTS.md
- .agents/scripts.md if present
- .agents/forge.md if the agent may open a PR/MR
- existing .agents/*.sh and .agents/*.json to avoid duplicate ids
Pick a short kebab-case id, a clear title, a one-line description, and a lucide icon name.
Write the bash script. Prefer deterministic checks first, cap any context passed to an LLM, then call an LLM only when useful.
Write the sidecar JSON.
Verify the script is executable and summarize the paths.

Script contract

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:

Cap logs and file lists before interpolation (tail -200, head -100, rg -n -C2 ... | head -160). Prefer letting the engine open a specific path over pasting whole files into the prompt.
Never merge to main/master.
Open a PR/MR only when the script creates concrete code changes.
Use terminal-cli ticket for findings the agent should not fix in the same run.
Use terminal-cli hitl only for true human blockers.
Treat HITL as append-only: do not edit 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 non-zero on real failure; exit 0 for no-op success.

Sidecar JSON

{
  "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.

Confirmation

End with the created/updated script path, sidecar path, and how to run it from TerMinal.

More from this repository

same repository

check

trevormil/offline-first-sportsbook

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.

2026-06-070

code-review

trevormil/offline-first-sportsbook

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'.

2026-06-070

emergency-fix

trevormil/offline-first-sportsbook

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'.

2026-06-070

factory

trevormil/offline-first-sportsbook

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'.

2026-06-070

new-persistent-agent

trevormil/offline-first-sportsbook

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.

2026-06-070

pr-creation

trevormil/offline-first-sportsbook

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'.

2026-06-070

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.

/new-agent — Create a TerMinal 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.

Target files

Default target is the current repo:

.agents/<id>.sh — executable script body (chmod 755)
.agents/<id>.json — metadata sidecar

If the user explicitly asks for a global agent, write to ~/.config/TerMinal/scripts/<id>.sh and <id>.json instead.

Workflow

Read enough local context before writing:
- CLAUDE.md / AGENTS.md
- .agents/scripts.md if present
- .agents/forge.md if the agent may open a PR/MR
- existing .agents/*.sh and .agents/*.json to avoid duplicate ids
Pick a short kebab-case id, a clear title, a one-line description, and a lucide icon name.
Write the bash script. Prefer deterministic checks first, cap any context passed to an LLM, then call an LLM only when useful.
Write the sidecar JSON.
Verify the script is executable and summarize the paths.

Script contract

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:

Cap logs and file lists before interpolation (tail -200, head -100, rg -n -C2 ... | head -160). Prefer letting the engine open a specific path over pasting whole files into the prompt.
Never merge to main/master.
Open a PR/MR only when the script creates concrete code changes.
Use terminal-cli ticket for findings the agent should not fix in the same run.
Use terminal-cli hitl only for true human blockers.
Treat HITL as append-only: do not edit 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 non-zero on real failure; exit 0 for no-op success.

Sidecar JSON

{
  "id": "kebab-case",
  "title": "Short label",
  "description": "One-line summary",
  "icon": "Bot",
  "opensPr": false,
  "engine": "claude",
  "model": "haiku",
  "inPlace": false
}

Confirmation

End with the created/updated script path, sidecar path, and how to run it from TerMinal.