Use this skill to install the seven oh-my-openspec role agent files for Codex, approve its OpenSpec MCP server, and verify setup. It checks existing files and avoids replacing differing files unless explicitly forced.
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.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
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.
List ~/.codex/agents/omos-*.toml. The seven expected roles:
omos-critic, omos-implementer, omos-planner, omos-researcher,
omos-retrospector, omos-reviewer, omos-verifier.
# managed-by: marker is our own and updates silently; a foreign
differing file is refused — replacing it is the user's explicit
--force choice.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.
Run node <root>/plugins/oh-my-openspec/assets/install-agents.mjs.
~/.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..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
openspec MCP server when Codex prompts — it provides
openspec_validate as mcp__openspec__openspec_validate.~/.codex/agents/omos-*.toml,
byte-identical to the installer's sources.spawn_agent can
name the roles and mcp__openspec__openspec_validate answers.~/.codex/config.toml — codex plugin add owns plugin
enablement.~/.codex/agents/omos-*.toml —
files without the # managed-by: marker need the user's explicit
--force choice; marker-carrying files are ours and update silently.No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Plan worthwhile local tasks by checking dependencies, effects, resources, and platform boundaries, then execute the exact approved plan. It can use safe parallel work or suitable Apple-silicon backends when the project exposes them.
Record deferred engineering decisions and temporary workarounds in a debt registry, with context such as effort, ongoing cost, affected area, and payoff trigger. Entries receive short labels so they can be reviewed or dropped later.
Generate or compare AI agent code for LangChain, EINO, AutoGen, AgentScope, and CrewAI using framework-specific templates, API mappings, conventions, and project structures. Reference files include verification dates to help identify potentially outdated guidance.
Investigate a reproducible bug, test failure, or unexpected page behavior, then make a narrowly scoped fix. The workflow calls for a regression test before changing code, verifies the fix, and reports remaining risks and evidence while avoiding unrelated refactoring or feature work.
Build an AI agent project through six collaborative stages, from requirements and architecture to tools, prompts, code generation, and verification. Start framework-independent, then generate a runnable project for frameworks such as LangChain, EINO, AutoGen, AgentScope, or CrewAI.
Audit a project or learning workflow for scope drift, conflicting plans, inconsistent names, and code quality concerns. The skill reads project files and code, then reports evidence, severity, and suggested next steps without changing files.