Skip to content
cccskills
FreePublished on GitHub

opencode-delegation

Delegates tasks to OpenCode (opencode run) via delegation-core. Use when delegation-core selects OpenCode or a provider-agnostic harness is wanted.

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md3.9 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

OpenCode Delegation

Overview

OpenCode is an open-source, provider-agnostic terminal agent published as npm opencode-ai. Its scripting entry point is opencode run, which takes the prompt as positional arguments.

Being provider-agnostic makes it the most flexible entry in the registry: the model behind it is whatever the local OpenCode config selects, including a local one.

When To Use

  • delegation-core selected opencode for the task
  • A provider the registry does not model directly is wanted, and OpenCode already has it configured
  • A local or self-hosted model should serve the request

When NOT To Use

  • No provider credentials are configured. opencode auth list shows what is present
  • A specific model must be pinned from this side. Model choice belongs to OpenCode's own config, not to the delegation call

Prerequisites

Installation

npm install -g opencode-ai@latest

Homebrew, pnpm, bun, scoop and chocolatey are also documented upstream.

Authentication

Credentials resolve per provider through environment variables such as ANTHROPIC_API_KEY or OPENAI_API_KEY, through a .env file, or through opencode auth login. Stored credentials are written to ~/.local/share/opencode/auth.json, and the config file supports {env:VARIABLE_NAME} interpolation.

Verification runs opencode auth list, because there is no single variable to check when the provider set is open-ended.

Quick Start

Using the shared delegation executor

uv run python scripts/delegation_executor.py opencode "Find the bug" \
  --files src/

Through the Makefile

make -C plugins/conjure delegate-opencode PROMPT='Find the bug'

Direct CLI usage

opencode run "Explain the use of context in this package"

Smart Delegation

opencode declares the code_execution strength and ranks last among the network providers in the candidate order, ahead only of the local glimmer service. It declares no model ids, since model choice belongs to OpenCode's own configuration.

OpenCode-Specific Details

PropertyValue
Binaryopencode
Packageopencode-ai
Headless formopencode run <prompt>
Prompt deliverypositional
Version probeopencode --version
Auth probeopencode auth list

opencode run --file <path> attaches a file upstream, but this service inlines file context into the prompt instead, which keeps one delivery path across every provider that lacks an @path syntax.

opencode serve starts a headless HTTP server that opencode run --attach <url> can target, and it honors OPENCODE_SERVER_PASSWORD. That path is not modeled here: the registry spawns a process per delegation rather than holding a server.

An output-format flag is documented for the session list, export and db subcommands, but not confirmed for run, so none is declared.

Exit Criteria

  • opencode resolves on PATH and answers opencode --version
  • opencode auth list shows at least one configured provider
  • The built command is opencode run <prompt> with the prompt last and no prompt flag before it
  • File context was inlined into the prompt rather than passed with --file
  • Output saved to delegations/opencode/YYYYMMDD_HHMMSS.md
  • This skill ran because delegation-core selected opencode

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Shapes turns action-first: action leads, steps numbered, state restated. Use for ADHD-friendly output. Do not use to trim tokens; use response-compression.

The English summary is being prepared. Showing the original description.

athola/claude-night-market342Updated Oct 17, 2026

Inverts burden of proof for code additions. Use when reviewing PRs, planning refactors, or running unbloat to challenge every addition's necessity.

The English summary is being prepared. Showing the original description.

athola/claude-night-market342Updated Oct 17, 2026

Tracks per-agent token usage and flags waste in parallel dispatch. Use when evaluating parallel agent efficiency or after a multi-agent run.

The English summary is being prepared. Showing the original description.

athola/claude-night-market342Updated Oct 17, 2026

Coordinates Claude agent teams via filesystem protocol. Use when orchestrating parallel agents with task dependencies. Do not use for single-agent tasks.

The English summary is being prepared. Showing the original description.

athola/claude-night-market342Updated Oct 17, 2026

Evaluates API surface design, consistency, and exemplar alignment. Use when reviewing public API changes or before releasing a new API surface.

The English summary is being prepared. Showing the original description.

athola/claude-night-market342Updated Oct 17, 2026

Selects architecture paradigm via research before scaffolding. Use when architecture is undecided and the choice needs justification and documentation.

The English summary is being prepared. Showing the original description.

athola/claude-night-market342Updated Oct 17, 2026

See all skills by athola

Report a problem with this skill