use-coding-agentslisted
Install: claude install-skill av/skills
# Use Coding Agents — Installed CLIs as Plain Sub-agents
Validated on `fedora` 2026-09-04 by running each command on a minimal prompt (write one file, or
reply OK). `pop-os` is set up identically via `control/install.sh`. Run `hostname` first.
Re-run `<agent> --help` before relying on any flag not listed here.
## Principle
Every agent here is a **worker**: it receives a prompt, edits files in one directory, commits,
prints a result, exits. Nothing more.
- **Do not use the CLIs' own orchestration features.** No `droid --mission`, no codex
`multi_agent`, no hermes `delegate_task` / `moa` / `kanban`, no `grok --agents`, no opencode
personas. Those are unvalidated here, spend tokens invisibly, and hide state from the orchestrator.
- **The orchestrator is the session running this skill** (normally claude via the Agent tool or a
lifeos skill). It plans units, writes prompts, launches workers, reads short results.
- Workers are interchangeable. Pick by availability and cost, not by feature.
## Workers
| Agent | Invocation | Auto-approve | Status 2026-09-04 |
|----------|-----------------------------------------------------------|------------------------------------------------|-------------------|
| claude | `claude -p "<prompt>"` | `--dangerously-skip-permissions` | PASS |
| codex | `codex exec "<prompt>"` (or prompt on stdin)