agentleFS
Sign inStart free
RohiRIKRohiRIK/skills/skills/OpenCode/SKILL.md

OpenCode

Skill1 starsChanged 30 days agoMITView on GitHub

Delegate a coding, refactor, or PR-review task to the OpenCode CLI as an autonomous worker. USE WHEN delegating such a task to OpenCode, or running the opencode CLI.

35 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use github-repo-management, touchdesigner-mcp and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • math-incSkill

    github-repo-management

    Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.

    Also in 14 projects that use this

  • john-data-chenSkill

    touchdesigner-mcp

    Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.

    Also in 7 projects that use this

  • math-incSkill

    minecraft-modpack-server

    Set up a modded Minecraft server from a CurseForge/Modrinth server pack zip. Covers NeoForge/Forge install, Java version, JVM tuning, firewall, LAN config, backups, and launch scripts.

    Also in 5 projects that use this

  • john-data-chenSkill

    teams-meeting-pipeline

    Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.

    Also in 8 projects that use this

  • Tommy-ywSkill

    songwriting-and-ai-music

    Songwriting craft, AI music generation prompts (Suno focus), parody/adaptation techniques, phonetic tricks, and lessons learned. These are tools and ideas, not rules. Break any of them when the art calls for it.

    Also in 10 projects that use this

  • mae616Skill

    p5js

    p5.js（クリエイティブコーディング）のProcessing由来「コードでスケッチ」思想を軸に、setup/drawループ・座標系・インタラクション・パフォーマンス最適化を整理する。p5.js、Processing、クリエイティブコーディング、ジェネラティブアート、インタラクティブ表現、ビジュアルプログラミング、Canvas描画、パーティクル、フラクタル、ノイズ表現に関する相談で必ず使うこと。ユーザーが「コードでアート」「動くビジュアル」「インタラクティブな描画」と言った場合にも適用する。

    Also in 10 projects that use this

  • +4 more from math-inc

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 0 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 32 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Always wrap runs in timeout (see Reference.md → Timeouts) so a stalled run self-kills instead of hanging the session.

    line 35
  2. Very specific:

    Read $ARGUMENTS, classify intent, load the matching workflow.

    line 41
  3. Very specific:

    Always preflight opencode --version and confirm a provider before the first run.

    line 51
  4. Very specific:

    Default to opencode run '<prompt>' (non-interactive).

    line 52

“Common” is measured: kept by at least 6 in 10 of the 32 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

OpenCode

Delegate work to the OpenCode CLI — a provider-agnostic autonomous coding agent — and orchestrate it from this session via Bash.

This skill runs when you type /opencode <task>, and Claude may also auto-invoke it when a task should be delegated to OpenCode. To make it manual-only again, add disable-model-invocation: true to the frontmatter and drop the USE WHEN clause from the description.

Task to delegate: $ARGUMENTS

How delegation maps to Claude Code tools

OpenCode runs as a subprocess. Orchestrate it with native tools:

NeedTool
Bounded one-shot task (waits for result)Bash (foreground)
Long / multi-file taskBash with run_in_background: true
Watch a backgrounded runBashOutput (poll) or Monitor (block until done)
Working directoryopencode run … --dir <path> (preferred over cd)

Always wrap runs in timeout (see Reference.md → Timeouts) so a stalled run self-kills instead of hanging the session. Default model when none is given: opencode/deepseek-v4-flash-free.

Workflow Routing

Read $ARGUMENTS, classify intent, load the matching workflow.

IntentTrigger wordsFile
Implement / refactor / fix"add", "build", "refactor", "fix", "implement"Workflows/Delegate.md
Review a PR or diff"review PR", "review pr #", "review diff"Workflows/ReviewPR.md

Quick Reference

  • Flags, models, install, binary pinning, troubleshooting: read Reference.md.
  • Always preflight opencode --version and confirm a provider before the first run.
  • Default to opencode run '<prompt>' (non-interactive). Never start the bare TUI (opencode with no subcommand) — it is interactive and will hang this session.

Gotchas

  • OpenCode runs autonomously — scope the task and verify the diff; treat its output as a worker's draft, not finished truth.
  • Non-zero exit writes failure context to .agent-state.md so the next loop/orchestrate pass replans rather than repeating.

Examples

Example 1: Delegate a coding task

User: "have opencode add pagination to the list endpoint"
→ Delegate workflow → runs autonomously → diff verified before reporting

Example 2: PR review

User: "opencode review this PR"
→ ReviewPR workflow → findings summarized

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free