omos-setup
Install the oh-my-openspec Codex host pieces: the seven ~/.codex/agents/omos-*.toml role agents via the bundled installer, then the openspec MCP-server approval. Invoke via $oh-my-openspec:omos-setup.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-11
- Stars
- ★ 1.6k
- Forks
- 474
01 前言 Front Matter
- name
- omos-setup
- description
- Install the oh-my-openspec Codex host pieces: the seven ~/.codex/agents/omos-*.toml role agents via the bundled installer, then the openspec MCP-server approval. Invoke via $oh-my-openspec:omos-setup.
03 SKILL.md 正文
omos-setup
Install this plugin's Codex host pieces once per machine: the seven role
agent TOMLs under ~/.codex/agents/, then the openspec MCP-server
approval. Run it after codex plugin add oh-my-openspec@oh-my-openspec,
or any time spawn_agent reports an unknown omos-* agent. This skill
acts directly — it dispatches no roles. You never run git write
commands.
Flow
1. Check current state
List ~/.codex/agents/omos-*.toml. The seven expected roles:
omos-critic, omos-implementer, omos-planner, omos-researcher,
omos-retrospector, omos-reviewer, omos-verifier.
- All seven present and unchanged → already installed; say so and go to §4 only if the approval is still missing.
- Any missing → continue with §2.
- Any differing → continue with §2. The installer plans each file as
copy, skip, update, or conflict: a differing file that carries the
# managed-by:marker is our own and updates silently; a foreign differing file is refused — replacing it is the user's explicit--forcechoice.
2. Locate the marketplace root
Run codex plugin marketplace list and read the oh-my-openspec
entry's local source path — the on-disk clone of this repository. That
clone is <root> for §3.
3. Run the installer
Run node <root>/plugins/oh-my-openspec/assets/install-agents.mjs.
- It copies the seven TOMLs into
~/.codex/agents/(created when missing), skips byte-identical files — a second run reports seven skips, zero copies — and refuses per file to clobber a differing target unless the user passed--force. - It prints the §4 approval and restart steps itself.
- Node ≥ 22.18 is required (the bundled MCP server imports
.ts); the installer warns below that floor.
Alternative for users who prefer a fresh clone — read-only, no plugin install needed:
git clone https://github.com/alexeyco/oh-my-openspec /tmp/oh-my-openspec &&
node /tmp/oh-my-openspec/plugins/oh-my-openspec/assets/install-agents.mjs
4. Approval and restart
- Approve the
openspecMCP server when Codex prompts — it providesopenspec_validateasmcp__openspec__openspec_validate. - Restart the session so the agents and the MCP server load.
5. Verify
- Re-run the §1 check: exactly seven
~/.codex/agents/omos-*.toml, byte-identical to the installer's sources. - Ask the user to confirm, in a fresh session, that
spawn_agentcan name the roles andmcp__openspec__openspec_validateanswers.
Guardrails
- Never write
~/.codex/config.toml—codex plugin addowns plugin enablement. - Never overwrite a FOREIGN differing
~/.codex/agents/omos-*.toml— files without the# managed-by:marker need the user's explicit--forcechoice; marker-carrying files are ours and update silently. - Never commit, push, or stage anything.
04 同仓库更多 Skills
migrate-to-e2e
Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for /migrate-to-e2e, "migrate our tests to e2e", "port these Maestro flows", "move our TesterArmy tests", or when a project has an e2e config and an older suite still running.
e2e
Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.
create-verification-skill
Generate a project-local verify-<app> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for /create-verification-skill, "make a verification skill for this repo", or when a project has no scripted way to prove UI behavior.
deja-search
deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.
deja-reflect
End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.
revid
Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.