AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

opencode QA Toolkit

Case-by-case QA of opencode itself — CLI, HTTP server, plugin hooks/events over SSE, tmux TUI smoke, and read-only session DB investigation.

Dev & CodingAdvanced★ 70,787⑂ 5,845AI score 8/10Last updated: Nov 8, 2026

What it does

Maps every opencode QA need to a tested helper script and a deep reference:

  • Case A – CLI: assert non-interactive runs with opencode run --format json, plus db path, session list, models
  • Case B – Server & hooks: open the GET /event SSE stream to prove a specific hook/action/event fired; smoke /global/health, /doc, and auth (401 without password)
  • Case C – TUI: boot the TUI under tmux in an isolated sandbox, confirm render and key delivery; use the xterm.js web-terminal path when true-color screenshot evidence is needed
  • Case D – Session DB: read-only lookups in opencode.db by session id, title, or message text, and full-session JSON export

Every script has a --self-test, and anything that spawns opencode runs inside an isolated XDG sandbox so the real database stays clean.

Who it's for

  • Contributors and maintainers working on opencode or its plugins
  • Plugin authors who need proof that a hook actually fired
  • Anyone debugging historical opencode sessions from the DB
  • Not useful if you don't run opencode.

Examples

  1. "Verify my plugin's message.part.updated hook fires" → watch a real server with sse-hook-probe.sh --attach ... --event message.part.updated, then trigger via POST /session/<id>/prompt_async
  2. "Find the recent session that logged 'permission denied'" → db-session-by-text.sh --recent 50 "permission denied" (scoped, because the part table is multi-GB)
  3. "Smoke-test the TUI" → tui-smoke.sh --self-test renders under tmux, tears down, and proves the real DB session count is unchanged

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/code-yeongyu/oh-my-openagent/HEAD/.agents/skills/opencode-qa/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the .agents/skills/opencode-qa folder from the GitHub repo code-yeongyu/oh-my-openagent into my ~/.claude/skills/opencode-qa/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/code-yeongyu/oh-my-openagent.git && mkdir -p ~/.claude/skills && cp -r oh-my-openagent/.agents/skills/opencode-qa ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Prerequisites: opencode, sqlite3, curl, jq, and tmux on PATH (macOS: brew install sqlite jq tmux).
  2. Clone the repo: git clone https://github.com/code-yeongyu/oh-my-openagent.git
  3. Copy the skill: mkdir -p ~/.claude/skills && cp -r oh-my-openagent/.agents/skills/opencode-qa ~/.claude/skills/
  4. Confirm the bundled scripts/ and references/ folders came along.
  5. Verify the harness: cd ~/.claude/skills/opencode-qa && bash scripts/lib/common.sh --self-check
  6. Restart Claude Code and ask things like "QA opencode", "verify this opencode hook", or "find an opencode session by id".
  7. Check your version with opencode --version and sanity-check flags with opencode <cmd> --help, since the skill was validated against v1.17.7.
View source on GitHub ↗License: NOASSERTION