Agent skill

OpenCode Delegation

by CherryHQ in CherryHQ/cherry-studio

Runs OpenCode once with opencode run and reads its JSON event stream, leaving its default denial of permission prompts in place for analysis.

AGPL-3.0Auto-check passedAgent Workflows

Install OpenCode Delegation

skills CLI
$ npx skills add CherryHQ/cherry-studio --skill code-mate-opencode -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install CherryHQ/cherry-studio code-mate-opencode --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/CherryHQ/cherry-studio.git skills-src && mkdir -p .claude/skills && cp -r skills-src/resources/code-cli-skills/code-mate-opencode .claude/skills/code-mate-opencode && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
code-mate-opencode
GitHub stars
52k
Token cost
~343 tokens
SKILL.md length
179 words
Files
1
Skills in repo
30
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Runs OpenCode once with opencode run and reads its JSON event stream, leaving its default denial of permission prompts in place for analysis.

  • Works in 3 steps: Set the Bash working directory to the… → Check availability with command -v… → Run one task and exit
  • Delegating a repository inspection to OpenCode
  • SKILL.md covers Run and Authentication And Permissions
  • Calls opencode

What it does

This skill lets the agent delegate repository analysis or coding work to OpenCode, or compare OpenCode's answer with another coding agent's. It sets the working directory to the project you named, applies a finite timeout of normally 10 minutes, confirms that `opencode` exists and then calls `opencode run` with the prompt as a single quoted argument and `--format json`.

Stdout is parsed as a JSON event stream, and an error event or a nonzero exit marks the run as failed. In headless mode OpenCode denies permission prompts by default, and the skill keeps that for analysis, enabling only the minimum tools when you explicitly want workspace changes and never adding `--auto` just to get past a denied permission. The agent avoids the interactive UI and authentication flow and asks you to configure a missing provider or credentials in Code Mate.

When your agent uses it

  • Delegating a repository inspection to OpenCode
  • Comparing OpenCode's diagnosis with another coding agent's
  • Letting OpenCode make an approved change with only the tools it needs

Example prompts

  • “Ask OpenCode to inspect the failing parser test without editing, then summarize its final reply.”
  • “Run OpenCode on ./frontend and report any tool errors it hit.”
  • “Compare what OpenCode and your own analysis say about the memory growth in the worker.”

Requirements

  • OpenCode installed through Code Mate
  • A provider and credentials configured in Code Mate

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Set the Bash working directory to the exact project the user named and set a finite timeout, normally 10 minutes.
  2. Check availability with command -v opencode. If it is missing, stop and ask the user to install OpenCode in Code Mate.
  3. Run one task and exit

What it can do on your machine

Read from SKILL.md and the folder at commit dd0767e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • opencode

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

OpenCode Delegation loads about 343 tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 179 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~48
When it runs · the whole SKILL.md, loaded when a task matches
~343

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from CherryHQ/cherry-studio at commit dd0767e, republished under its AGPL-3.0 licence (© CherryHQ). 179 words, ~343 tokens.

Download SKILL.mdSave it as .claude/skills/code-mate-opencode/SKILL.md (or your agent's skills folder).
name
code-mate-opencode
description
Runs OpenCode non-interactively for repository analysis and coding tasks. Use when the user asks to delegate work to OpenCode or compare OpenCode with another coding agent.

OpenCode

Run

  1. Set the Bash working directory to the exact project the user named and set a finite timeout, normally 10 minutes.
  2. Check availability with command -v opencode. If it is missing, stop and ask the user to install OpenCode in Code Mate.
  3. Run one task and exit:
bash
opencode run "<prompt>" --format json

Pass the prompt as one quoted argument. Parse stdout as a JSON event stream and treat an error event or nonzero exit as failure. Never start the interactive OpenCode UI or an authentication flow.

Authentication And Permissions

If OpenCode reports a missing provider or credentials, stop and ask the user to configure OpenCode in Code Mate. Never request, read, print, or copy credentials.

Headless mode denies permission prompts by default; keep that behavior for analysis. Only when the user explicitly requests workspace changes may the command enable the minimum tools needed. Do not add --auto merely to avoid a denied permission.

Example: ask OpenCode to inspect a failing test without editing, run the command above from that repository, and summarize the final content event and any tool errors.

© CherryHQ, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in resources/code-cli-skills/code-mate-opencode of CherryHQ/cherry-studio.

Open the folder on GitHubat commit dd0767e

Compare with similar skills

OpenCode Delegation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

OpenCode Delegation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
OpenCode Delegation this skillCherryHQ/cherry-studio52k—~343Automated safety check: PassAGPL-3.0
Cline Pilotsickn33/agentic-awesome-skills47k1 repos~4.6kAutomated safety check: PassMIT
Kode Permissions DebuggingshareAI-lab/Kode-CLI5.2k—~498Automated safety check: PassApache-2.0
Sol and Luna Worker Routermajiayu000/spellbook286—~3.3kAutomated safety check: PassMIT
Spk Run Program Orchestratespec-kitty/spec-kitty1.7k—~209Automated safety check: PassMIT
Dispatch Agentsdanielvm-git/bigpowers256—~1.3kAutomated safety check: PassMIT

Similar skills

  • Cline Pilot

    sickn33/agentic-awesome-skills

    Acts as a proxy for the Cline CLI, dispatching coding tasks one at a time, monitoring runs by hard evidence, relaying decisions to you and learning per-project preferences.

    47k GitHub starsUsed in 1 repo~4.6k tokens
    Agent WorkflowsAuto-check passed
  • Kode Permissions Debugging

    shareAI-lab/Kode-CLI

    Troubleshoots Kode permission prompts and denials, including allowlists, command-level tool limits, dontAsk mode and subagent inheritance, without loosening permissions.

    5.2k GitHub stars~498 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Sol and Luna Worker Router

    majiayu000/spellbook

    Splits substantial coding or repository-review work between a Sol commander that decides and verifies and a separate Luna Max worker that implements, with an auditable run log.

    286 GitHub stars~3.3k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Spk Run Program Orchestrate

    spec-kitty/spec-kitty

    Orchestrate multi-repo, multi-mission Spec Kitty programs across dependencies, parallel agents, review gates, merge, and post-merge closeout.

    1.7k GitHub stars~209 tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Dispatch Agents

    danielvm-git/bigpowers

    Dispatch multiple subagents in parallel on independent tasks.

    256 GitHub stars~1.3k tokensUpdated 16 days ago
    Agent WorkflowsAuto-check passed
  • Ship Feature

    theexperiencecompany/gaia

    Autonomously ship a feature end-to-end with zero human intervention: plan it, implement it, review it with a team of subagents, boot the full stack, drive it in a real browser like a user…

    308 GitHub stars~2.7k tokensUpdated today
    Agent WorkflowsAuto-check: notes

More from CherryHQ/cherry-studio

All 30 skills in this repo
  • Office File Transform

    CherryHQ/cherry-studio

    Derives new files from a selected part of a spreadsheet, Word document, PDF or slide deck, such as a cell range, paragraph, page or slide, without ever modifying the source file.

    52k GitHub stars~4.7k tokensUpdated today
    Auto-check passed
  • GitHub Issue Creator

    CherryHQ/cherry-studio

    Creates GitHub issues for the current repository by choosing the matching issue template and following its format, with a permission check for engineering tasks.

    52k GitHub stars~1.6k tokensUpdated today
    Auto-check passed
  • Cherry Studio PR Review

    CherryHQ/cherry-studio

    Reviews Cherry Studio branches, pull requests, commits, files and docs against the project's own architecture, naming, API-boundary and UI rules, report-only by default.

    52k GitHub stars~3.9k tokensUpdated today
    Auto-check passed
  • Cherry Studio Regression Tests

    CherryHQ/cherry-studio

    Runs Cherry Studio's critical-path regression suite as deterministic Playwright E2E tests through a GitHub workflow on macOS and Windows runners.

    52k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Antigravity CLI Runner

    CherryHQ/cherry-studio

    Runs the Antigravity CLI headlessly with the agy command to analyze a repository or carry out a coding task, then checks its JSON result and the diff.

    52k GitHub stars~531 tokensUpdated today
    Auto-check passed
  • Kimi Code Delegation

    CherryHQ/cherry-studio

    Delegates one bounded repository task to Kimi Code in non-interactive prompt mode and reads back the final result from its JSON event stream.

    52k GitHub stars~504 tokensUpdated today
    Auto-check passed

Categories

Questions about OpenCode Delegation

What does OpenCode Delegation do?

Runs OpenCode once with opencode run and reads its JSON event stream, leaving its default denial of permission prompts in place for analysis. This skill lets the agent delegate repository analysis or coding work to OpenCode, or compare OpenCode's answer with another coding agent's. It sets the working directory to the project you named, applies a finite timeout of normally 10 minutes, confirms that `opencode` exists and then calls `opencode run` with the prompt as a single quoted argument and `--format json`.

When should I use OpenCode Delegation?

OpenCode Delegation fits situations like: delegating a repository inspection to OpenCode; comparing OpenCode's diagnosis with another coding agent's; letting OpenCode make an approved change with only the tools it needs.

How do I install OpenCode Delegation in Claude Code?

Run `npx skills add CherryHQ/cherry-studio --skill code-mate-opencode -a claude-code`. Or copy the skill folder (resources/code-cli-skills/code-mate-opencode in CherryHQ/cherry-studio) into .claude/skills/code-mate-opencode in your project. Claude Code loads it when a task matches its description.

How do I install OpenCode Delegation in Codex?

Run `npx skills add CherryHQ/cherry-studio --skill code-mate-opencode -a codex`. Or copy the skill folder (resources/code-cli-skills/code-mate-opencode in CherryHQ/cherry-studio) into .agents/skills/code-mate-opencode in your project. Codex loads it when a task matches its description.

Can I use OpenCode Delegation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add CherryHQ/cherry-studio --skill code-mate-opencode -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/code-mate-opencode, .gemini/skills/code-mate-opencode, .github/skills/code-mate-opencode and .opencode/skills/code-mate-opencode in your project.

What does OpenCode Delegation need to run?

Going by SKILL.md and its folder, OpenCode Delegation needs the command-line tools its instructions call (opencode). Our summary lists: OpenCode installed through Code Mate; A provider and credentials configured in Code Mate.

Does OpenCode Delegation access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is OpenCode Delegation safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does OpenCode Delegation use?

OpenCode Delegation is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does OpenCode Delegation use?

About 343 tokens (SKILL.md is roughly 1.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to OpenCode Delegation?

Skills that share tags, products or a category with OpenCode Delegation: Cline Pilot (sickn33/agentic-awesome-skills, 47k stars), Kode Permissions Debugging (shareAI-lab/Kode-CLI, 5.2k stars), Sol and Luna Worker Router (majiayu000/spellbook, 286 stars) and Spk Run Program Orchestrate (spec-kitty/spec-kitty, 1.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains OpenCode Delegation?

CherryHQ (a GitHub organization) maintains it in CherryHQ/cherry-studio, which has 52,407 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on October 7, 2026.

Source: CherryHQ/cherry-studio on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.