Claude Code-style auto-continue, scheduled OpenCode work, and background loops.
OpenCode Loop adds /loop, scheduled prompt/command/shell jobs, compact scheduling, safe long-running continuation helpers, and the opencode-loopd background daemon.
Current release:
0.5.27. Loop also contains an older experimental/loop-goalmode, but for strong persistent Goal contracts and host-verified completion, use the separate OpenCode Goals plugin described below.
Choose either installation method below.
npx -y @bybrawe/opencode-loop@latestRun the same command again whenever you want to update.
Install OpenCode Loop globally so its installer and daemon commands are available:
npm install -g @bybrawe/opencode-loop@latest
opencode-loopTo update later:
npm install -g @bybrawe/opencode-loop@latest
opencode-loopnpm install @bybrawe/opencode-loop by itself only adds the Node package to the current project. For a normal OpenCode installation, use the global npm method above or the recommended npx installer.
The installer:
- installs/updates the OpenCode Loop plugin;
- installs the
/loop-*slash-command definitions; - installs the tool-denied
opencode-loop-localcommand agent; - keeps an existing npm plugin entry pinned to the installer’s exact version to avoid stale OpenCode package-cache resolution;
- removes duplicate old local Loop plugin copies when the package entry is authoritative.
Then fully restart OpenCode and verify:
/loop-help
/loop-doctor
If you use the npx installer:
npx -y @bybrawe/opencode-loop@latest --uninstallIf you installed OpenCode Loop globally with npm:
opencode-loop --uninstall
npm uninstall -g @bybrawe/opencode-loopRun opencode-loop --uninstall before removing the global npm package so it can clean its OpenCode registrations and managed command files.
Uninstall removes known OpenCode Loop package registrations, local plugin files, /loop-* command markdown files, and the Loop local command agent while preserving unrelated OpenCode configuration.
Project Loop state is intentionally preserved under:
.opencode/opencode-loop/
Delete that directory yourself only when you intentionally want to erase saved Loop jobs, logs, checkpoints, or related local state. Restart OpenCode after uninstalling.
Auto-continue whenever OpenCode becomes idle:
/loop 0s continue from progress.md and implement the next unfinished TODO
Run a prompt every 5 minutes when idle:
/loop 5m continue the project
Wait before the first run:
/loop 5m --no-now continue the project
Schedule an OpenCode command such as compaction:
/loop-command 200m /compact
Run a real shell command on a schedule:
/loop-shell 10m npm test
Ask a recurring quality-control question:
/loop-ask 1h did you run tests, typecheck, and build? If not, run them and fix errors.
Use Loop when the important question is “what should run again, and when?”
Typical uses:
- Claude Code-style auto-continue after idle;
- recurring coding prompts;
- progress.md / TODO workflows;
- scheduled
/compactor other OpenCode commands; - recurring tests/lint/build shell jobs;
- retry/fix loops with verification;
- patch checkpoints;
- maximum run/runtime/failure limits;
- prompt-file workflows;
- background work through
opencode-loopd; - Windows Task Scheduler integration.
Loop is idle-safe: if a job becomes due while the session is busy, active tools or child work are still running, the job waits instead of intentionally stacking another turn on top of the current one.
OpenCode Loop still includes the older experimental /loop-goal workflow. It is useful for compatibility and lightweight outcome-driven automation, but it is not the strongest Goal implementation in this project family.
For durable Goal Contracts, host-owned evidence, semantic verification, native Todo coordination, revision isolation, false-completion protection, restart recovery, Goal audit, budgets, and ordered Goals, install OpenCode Goals.
Recommended one-command installer:
npx -y @bybrawe/opencode-goal@latestOr install its CLI globally with npm and run the installer:
npm install -g @bybrawe/opencode-goal@latest
opencode-goalThen use:
/goal <objective>
/goal status
/goal contract
/goal audit
Yes. @bybrawe/opencode-loop and @bybrawe/opencode-goal use different package names, commands, and project-state directories, so they can coexist in one OpenCode installation.
Recommended split:
- use
/goalfor persistent, strongly verified outcome completion; - use
/loop,/loop-command,/loop-shell, andopencode-loopdfor scheduling/repetition/background infrastructure.
Do not run Loop’s /loop-goal and OpenCode Goals /goal against the same work in the same session. Both can autonomously continue on idle boundaries and can compete to start turns.
Likewise, avoid leaving a prompt-producing /loop ... job continuously injecting agent turns into a session while an OpenCode Goal is actively continuing. Use separate sessions or pause/remove that prompt loop until the Goal is done. Scheduled shell/command jobs should also be chosen carefully so they do not race files or verification.
Install both when needed with npx:
npx -y @bybrawe/opencode-loop@latest
npx -y @bybrawe/opencode-goal@latestOr install both globally with npm, then run both installers:
npm install -g @bybrawe/opencode-loop@latest @bybrawe/opencode-goal@latest
opencode-loop
opencode-goal| Command | Purpose |
|---|---|
/loop <interval> <prompt> |
Add/update an idle/interval prompt loop |
/loop-command <interval> <slash-command> |
Schedule OpenCode slash commands |
/loop-cmd <interval> <slash-command> |
Alias for /loop-command |
/loop-ask <interval> <question> |
Schedule recurring quality/check prompts |
/loop-shell <interval> <command> |
Schedule a real shell command |
/loop-status |
Show active jobs |
/loop-now [id/name/all] |
Run selected jobs immediately |
/loop-pause [id/name/all] |
Pause jobs |
/loop-resume [id/name/all] |
Resume jobs |
/loop-remove [id/name/all] |
Remove jobs |
/loop-clear |
Remove all current-session Loop jobs |
/loop-doctor |
Diagnose Loop/OpenCode state |
/loop-init |
Create a starter progress.md |
/loop-export |
Export Loop state as JSON |
/loop-goal <objective> |
Start the older experimental Loop Goal Mode |
Examples:
0s run whenever OpenCode becomes idle
5m run every 5 minutes when idle
200m run every 200 minutes when idle
1h run every hour when idle
OpenCode Loop separates prompt, slash-command, and shell work because they should not be executed the same way.
| Type | Example |
|---|---|
| Prompt | /loop 0s continue from progress.md |
| Scheduled question | /loop-ask 1h did you run tests? |
| OpenCode command | /loop-command 200m /compact |
| Shell | /loop-shell 10m npm test |
Do not use a normal prompt loop when you mean to run /compact. Prefer:
/loop-command 200m /compact
/loop 0s --name dev continue the project
/loop-pause dev
/loop-resume dev
/loop-stop dev
--max-runs <n>
--max-runtime <duration>
--max-failures <n>
--timeout <duration>
--verify "npm test"
--preflight "npm install"
--postrun "git status --short"
--pause-on-verify-fail
--safe
--ask-never
--no-overlap
--progress-file progress.md
--prompt-file loop-prompt.md
--include-file ARCHITECTURE.md
--batch 5
--compact-every 20
--watch progress.md
--checkpoint-only
--git-checkpoint
--git-checkpoint may stage and commit work. Use it only when that behavior is intentional.
/loop 0s --name dev --ask-never --safe --no-overlap --batch 5 --compact-every 200m --checkpoint-only --progress-file progress.md Treat progress.md as the project state. Continue with the next unfinished TODO, implement it, mark completed items, add useful follow-up TODOs, run tests/lint/build when available, and keep going while work remains.
/loop 0s --name testfix --ask-never --safe --verify "npm test" --max-failures 3 Continue from progress.md. If tests fail, analyze the failure, fix it, and run the tests again.
The normal /loop plugin is session-bound. If OpenCode closes, that TUI/session loop cannot keep running in the background. opencode-loopd resolves the session once at startup and pins that exact session for later iterations, so a newer unrelated session cannot steal the daemon. If no session exists, the daemon creates one and pins it before the second iteration. Each daemon run is bounded by --timeout (30 minutes by default; use --timeout 0s to disable).
For long-running background jobs use:
opencode-loopd --project . --every 5m --prompt-file loop-prompt.mdRun immediately on each daemon iteration:
opencode-loopd --project . --every 0s --prompt "continue from progress.md and implement the next unfinished TODO"Select a model and agent:
opencode-loopd --project . --every 0s --max-runs 1 --timeout 30m --model provider/model --agent build --prompt-file loop-prompt.mdPin a specific existing session when needed:
opencode-loopd --project . --session ses_xxx --every 5m --prompt-file loop-prompt.mdLimit total runs:
opencode-loopd --project . --every 5m --max-runs 20 --prompt-file loop-prompt.mdInstall a scheduled daemon task:
opencode-loopd install-task --project "C:\path\to\project" --every 10m --prompt-file loop-prompt.md --name OpenCodeLoopRemove it:
opencode-loopd uninstall-task --name OpenCodeLoopLoop’s original Goal Mode remains available for existing users:
/loop-goal --check "npm test" --complete-when-checks-pass fix the failing tests
Controls:
/loop-goal-status
/loop-goal-pause
/loop-goal-resume
/loop-goal-clear
/loop-goal-done <summary>
/loop-goal-blocked <reason>
It supports acceptance criteria, check commands, evidence text, no-progress guards, turn/runtime limits, and reports under:
.opencode/opencode-loop/goals/
For new work where completion integrity matters, prefer the dedicated OpenCode Goals package instead:
npx -y @bybrawe/opencode-goal@latestor:
npm install -g @bybrawe/opencode-goal@latest
opencode-goalLoop runtime state:
.opencode/opencode-loop/
Patch checkpoints:
.opencode/opencode-loop/checkpoints/
Recent plugin events:
.opencode/opencode-loop/loop.log
Add .opencode/opencode-loop/ to .gitignore when you do not want runtime noise committed.
For unattended loops, avoid granting every shell command permanently. Allow routine read/edit/test operations and keep destructive operations on ask/deny.
Example:
{
"$schema": "https://opencode.ai/config.json",
"permission": {
"read": "allow",
"grep": "allow",
"glob": "allow",
"todowrite": "allow",
"edit": "allow",
"bash": {
"*": "ask",
"git status*": "allow",
"git diff*": "allow",
"npm test*": "allow",
"npm run test*": "allow",
"npm run lint*": "allow",
"git push*": "ask",
"git reset*": "ask",
"git clean*": "deny",
"rm *": "deny"
},
"external_directory": "ask"
}
}--safe reduces risk but does not replace careful OpenCode permission configuration.
@bybrawe/opencode-loop
The package also installs:
opencode-loop --help
opencode-loopd --helpSee CHANGELOG.md for release history.
MIT