DeerFlow Smoke Test
bytedance/deer-flow
Walks through an end-to-end smoke test of a DeerFlow deployment: pull the latest code, deploy with Docker or locally, verify services, run health checks and write a report.
Tests the opencode coding agent itself: its CLI, server, plugin hooks and events, the terminal UI under tmux, and its SQLite session database, using tested helper scripts.
Install OpenCode QA Toolkit
$ npx skills add code-yeongyu/oh-my-openagent --skill opencode-qa -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install code-yeongyu/oh-my-openagent opencode-qa --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/code-yeongyu/oh-my-openagent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/opencode-qa .claude/skills/opencode-qa && rm -rf skills-srcUse ~/.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/
Install the "opencode-qa" agent skill from https://github.com/code-yeongyu/oh-my-openagent/tree/dev/.agents/skills/opencode-qa into .claude/skills/opencode-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "opencode-qa", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/code-yeongyu/oh-my-openagent/tree/dev/.agents/skills/opencode-qaType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add code-yeongyu/oh-my-openagent --skill opencode-qa -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install code-yeongyu/oh-my-openagent opencode-qa --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/code-yeongyu/oh-my-openagent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/opencode-qa .agents/skills/opencode-qa && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "opencode-qa" agent skill from https://github.com/code-yeongyu/oh-my-openagent/tree/dev/.agents/skills/opencode-qa into .agents/skills/opencode-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "opencode-qa", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add code-yeongyu/oh-my-openagent --skill opencode-qa -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install code-yeongyu/oh-my-openagent opencode-qa --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/code-yeongyu/oh-my-openagent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/opencode-qa .cursor/skills/opencode-qa && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "opencode-qa" agent skill from https://github.com/code-yeongyu/oh-my-openagent/tree/dev/.agents/skills/opencode-qa into .cursor/skills/opencode-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "opencode-qa", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/code-yeongyu/oh-my-openagent.git --path .agents/skills/opencode-qa--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add code-yeongyu/oh-my-openagent --skill opencode-qa -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install code-yeongyu/oh-my-openagent opencode-qa --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/code-yeongyu/oh-my-openagent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/opencode-qa .gemini/skills/opencode-qa && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "opencode-qa" agent skill from https://github.com/code-yeongyu/oh-my-openagent/tree/dev/.agents/skills/opencode-qa into .gemini/skills/opencode-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "opencode-qa", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install code-yeongyu/oh-my-openagent opencode-qaInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add code-yeongyu/oh-my-openagent --skill opencode-qa -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/code-yeongyu/oh-my-openagent.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/opencode-qa .github/skills/opencode-qa && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "opencode-qa" agent skill from https://github.com/code-yeongyu/oh-my-openagent/tree/dev/.agents/skills/opencode-qa into .github/skills/opencode-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "opencode-qa", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add code-yeongyu/oh-my-openagent --skill opencode-qa -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install code-yeongyu/oh-my-openagent opencode-qa --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/code-yeongyu/oh-my-openagent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/opencode-qa .opencode/skills/opencode-qa && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "opencode-qa" agent skill from https://github.com/code-yeongyu/oh-my-openagent/tree/dev/.agents/skills/opencode-qa into .opencode/skills/opencode-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "opencode-qa", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
opencode-qa- GitHub stars
- 70k
- Token cost
- ~2.9k tokens
- SKILL.md length
- 1,129 words
- Files
- 22 (incl. scripts, references)
- Skills in repo
- 44
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Tests the opencode coding agent itself: its CLI, server, plugin hooks and events, the terminal UI under tmux, and its SQLite session database, using tested helper scripts.
- Smoke-testing an opencode build or its CLI commands
- SKILL.md covers Golden rules (read before…, Setup, Router: pick your case and Case A: CLI / terminal works, plus 6 more sections
- Runs Shell and JavaScript scripts from its folder; calls opencode, bash and curl; needs OPENCODE_SERVER_PASSWORD
- Proving that a plugin hook or event actually fired
What it does
The skill maps each QA need to a bundled helper script and a deeper reference. Cases include checking CLI commands such as `opencode run`, proving that a plugin hook, action or event fired by watching the server's event stream, smoke-testing the terminal UI inside tmux, and looking up sessions in opencode's SQLite database by id, name or message text. Every script ships a `--self-test`, so the scripts double as their own regression checks.
Golden rules keep QA safe: reading the live database is fine, but anything that starts opencode must use an isolated XDG sandbox so test sessions never land in the real database, and text searches over the large message-part table must be scoped by session, recency or date, which the script enforces. Docker is the default QA surface through a disposable container, with the local scripts as a fallback, including on Windows. The shared harness requires opencode, sqlite3, curl, jq and tmux on the path.
When your agent uses it
- Smoke-testing an opencode build or its CLI commands
- Proving that a plugin hook or event actually fired
- Finding an opencode session by id, title or message text
- Checking the opencode HTTP server health and event stream
- Testing the terminal UI under tmux
Example prompts
- “Find the opencode session whose messages mention the deploy failure, limited to the last day.”
- “Verify that my plugin's hook fires, using the event stream.”
- “Run a smoke test of opencode serve in an isolated sandbox.”
- “QA the TUI under tmux and tell me what breaks.”
Requirements
- opencode, sqlite3, curl, jq and tmux on the PATH
- Docker for the default disposable QA container
What it can do on your machine
Read from SKILL.md and the folder at commit cbd7dd2. 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
Ships 9 files in scripts/ (Shell and JavaScript, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
opencodebashcurlnodebunsqlite3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
OPENCODE_SERVER_PASSWORD
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
OpenCode QA Toolkit loads about 2.9k tokens when it runs, and up to ~13k if it reads all its reference files. Until then it costs about 187 tokens; SKILL.md has 1,129 words of instructions outside code blocks.
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); the scripts in this folder are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,129 words (~2,885 tokens).
“QA the opencode coding agent itself. This skill maps each QA need to a tested helper script and a deep reference. Every script ships a --self-test that asserts its scenario against the live machine, so the scripts are both the…”
- name
- opencode-qa
Files
SKILL.md and 21 other files (scripts, references) in .agents/skills/opencode-qa of code-yeongyu/oh-my-openagent.
- SKILL.md
- references/cli-commands.md
- references/db-investigation.md
- references/docker-qa.md
- references/events-hooks.md
- references/sdk.md
- references/server-api.md
- references/testing-harness.md
- references/tui-tmux.md
- scripts/db-session-by-id.sh
- scripts/db-session-by-name.sh
- scripts/db-session-by-text.sh
- scripts/export-roundtrip.sh
- scripts/lib/common.sh
- scripts/lib/fake-openai-branches.mjs
- scripts/lib/fake-openai-events.mjs
- scripts/lib/fake-openai-server.mjs
- scripts/lsp-e2e.sh
- … and 4 more
Open the folder on GitHubat commit cbd7dd2
Compare with similar skills
OpenCode QA Toolkit 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| OpenCode QA Toolkit this skillcode-yeongyu/oh-my-openagent | 70k | — | ~2.9k | Automated safety check: Pass | Custom licence | |
| DeerFlow Smoke Testbytedance/deer-flow | 83k | — | ~2.5k | Automated safety check: Notes | MIT | |
| CodexBar Live QAsteipete/CodexBar | 22k | — | ~1.2k | Automated safety check: Pass | MIT | |
| OpenWork Desktop CDP Driverdifferent-ai/openwork | 24k | — | ~465 | Automated safety check: Pass | Custom licence | |
| Weavebench Cua ReproduceAMAP-ML/LongHorizon-Harness | 1.7k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Reproduce Chat Statesdifferent-ai/openwork | 24k | — | ~673 | Automated safety check: Pass | Custom licence |
Similar skills
CodexBar Live QA
steipete/CodexBar
Runs live QA for the CodexBar app: provider usage matrix checks through its packaged CLI, config validation and menu checks, with 1Password-backed credentials handled safely.
OpenWork Desktop CDP Driver
different-ai/openwork
Drives a running OpenWork desktop window over CDP from the shell to evaluate JS, take screenshots, start sessions and send prompts for hand checks.
Weavebench Cua Reproduce
AMAP-ML/LongHorizon-Harness
Reproduce CUA-Harness experiments on WeaveBench from a GitHub checkout.
Reproduce Chat States
different-ai/openwork
Fires known chat states in the running OpenWork desktop app, such as provider errors, retries and tool steps, so you can check how each renders.
Senpi Agent QA Harness
code-yeongyu/senpi
Checks changes to the senpi coding agent by driving the real CLI from source in an isolated sandbox, over RPC, terminal UI, mock model and CLI smoke channels.
More from code-yeongyu/oh-my-openagent
All 44 skills in this repoast-grep Structural Search
code-yeongyu/oh-my-openagent
Searches and rewrites code by syntax-tree shape across 25 languages with ast-grep, for codemods, structural queries and YAML lint rules, using a Python wrapper script.
Browser Control with Omowright
code-yeongyu/oh-my-openagent
Drives a real browser through the omowright library, either the user's own signed-in browser or a separate browser the code launches, for forms, QA, screenshots and scraping.
Codex Plugin QA
code-yeongyu/oh-my-openagent
Tests the omo Codex plugin in an isolated CODEX_HOME with a local mock model, proving hooks fired through app-server notifications without touching ~/.codex.
Coding Agent Session Finder
code-yeongyu/oh-my-openagent
Finds, reads and reconstructs past coding-agent sessions across Codex, Claude, OpenCode, Senpi and many other local agent logs.
LSP Setup
code-yeongyu/oh-my-openagent
Detects which languages a project uses, installs the matching language server, writes its config and checks it with a real call so diagnostics and go-to-definition work.
ULW Plan Workflow
code-yeongyu/oh-my-openagent
Explore-first planning that turns a vague or large request into one decision-complete work plan, written only after your approval and executed by a separate worker.
Related
Categories
Questions about OpenCode QA Toolkit
What does OpenCode QA Toolkit do?
Tests the opencode coding agent itself: its CLI, server, plugin hooks and events, the terminal UI under tmux, and its SQLite session database, using tested helper scripts. The skill maps each QA need to a bundled helper script and a deeper reference. Cases include checking CLI commands such as `opencode run`, proving that a plugin hook, action or event fired by watching the server's event stream, smoke-testing the terminal UI inside tmux, and looking up sessions in opencode's SQLite database by id, name or message text.
When should I use OpenCode QA Toolkit?
OpenCode QA Toolkit fits situations like: smoke-testing an opencode build or its CLI commands; proving that a plugin hook or event actually fired; finding an opencode session by id, title or message text; checking the opencode HTTP server health and event stream.
How do I install OpenCode QA Toolkit in Claude Code?
Run `npx skills add code-yeongyu/oh-my-openagent --skill opencode-qa -a claude-code`. Or copy the skill folder (.agents/skills/opencode-qa in code-yeongyu/oh-my-openagent) into .claude/skills/opencode-qa in your project. Claude Code loads it when a task matches its description.
How do I install OpenCode QA Toolkit in Codex?
Run `npx skills add code-yeongyu/oh-my-openagent --skill opencode-qa -a codex`. Or copy the skill folder (.agents/skills/opencode-qa in code-yeongyu/oh-my-openagent) into .agents/skills/opencode-qa in your project. Codex loads it when a task matches its description.
Can I use OpenCode QA Toolkit 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 code-yeongyu/oh-my-openagent --skill opencode-qa -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/opencode-qa, .gemini/skills/opencode-qa, .github/skills/opencode-qa and .opencode/skills/opencode-qa in your project.
What does OpenCode QA Toolkit need to run?
Going by SKILL.md and its folder, OpenCode QA Toolkit needs a shell and JavaScript for the scripts in its folder, the command-line tools its instructions call (opencode, bash, curl, node, bun and sqlite3) and credentials named OPENCODE_SERVER_PASSWORD. Our summary lists: opencode, sqlite3, curl, jq and tmux on the PATH; Docker for the default disposable QA container.
Does OpenCode QA Toolkit access the network?
SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is OpenCode QA Toolkit 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does OpenCode QA Toolkit use?
OpenCode QA Toolkit has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does OpenCode QA Toolkit use?
About 2.9k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9.7k tokens, read only when the agent opens those files.
What are the alternatives to OpenCode QA Toolkit?
Skills that share tags, products or a category with OpenCode QA Toolkit: DeerFlow Smoke Test (bytedance/deer-flow, 83k stars), CodexBar Live QA (steipete/CodexBar, 22k stars), OpenWork Desktop CDP Driver (different-ai/openwork, 24k stars) and Weavebench Cua Reproduce (AMAP-ML/LongHorizon-Harness, 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 QA Toolkit?
code-yeongyu (a GitHub user) maintains it in code-yeongyu/oh-my-openagent, which has 69,850 GitHub stars. The repository holds 44 skills in this directory. The repository was last updated on October 7, 2026.
Source: code-yeongyu/oh-my-openagent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.