Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →amelnagdy/opencode-delegate
Delegate a coding task to the OpenCode CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to OpenCode — phrasings like "have OpenCode do X", "delegate this to OpenCode", "run it through OpenCode", or "use OpenCode to implement/fix/refactor" — or wants to run a queue of coding tasks through OpenCode while staying the reviewer. Prefer it when the user will review the diff and commit it themselves. DO NOT USE for
Passed 15 of 20 test cases with the skill, and 5 of 20 without it.
and 9 more in the full report
11 fixed6 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.8-flash on 10/20/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
The orchestrator session is active in `~`, but the target codebase lives in `/var/projects/service`. Which option instructs relay.mjs to execute in that codebase path?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies passing --cd /var/projects/service to relay.mjs. | Missed | Passed |
The instructions your model reads when the skill loads.
You are the orchestrator. This skill lets you hand a bounded coding task to a separate implementer — the OpenCode CLI — then review what it produced and land it yourself. You write the brief and own the judgment; OpenCode does the typing in its own session; you verify and commit.
Nothing here is specific to one orchestrating agent. The loop needs only the ability to run a shell command and read a file, so any agent with those two capabilities — Claude Code, OpenCode driving a sibling session, or a comparable one — can drive it. (It is designed for and run on Claude Code; treat other orchestrators as designed-for, not yet proven.)
opencode CLI is not installed or not authenticated (run opencode auth login).plan agent via --read-only).opencode --version succeeds. If not, install (npm i -g opencode-ai, or the native installer from
opencode.ai) and opencode auth login.opencode is on PATH. command -v opencode shows the active binary and
opencode --version its version. The relay records the version it ran into result.json, so a stale
binary is visible after the fact.opencode auth list shows at least one credential.--cd at) the target git repository.OpenCode has no safe default — a bare opencode run errors — so a fresh run needs a model via
--model or a fleet --lane that sets one (a resumed run inherits its session's model). Naming the
model is the one decision a single-model backend like codex-delegate never had, and it has two owners:
opencode models lists hundreds of entries, most billed
per token (OpenRouter and the like); only the human knows which are their flat-rate subscriptions, and
the CLI can't tell them apart. So the usable set is theirs — ideally stated once in the repo's
AGENTS.md or their CLAUDE.md (e.g. "delegate mechanical work to opencode-go/…, hard logic to
…").test cases passed, vs 5 / 20 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.