Claude Essentials plugin
The ce plugin for Claude Code and Codex: eleven skills and four sub-agents for plans, review, tests, architecture and writing.
- 132 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Sub-agents read repository code, and executing-plans edits files and performs a local merge to main.
- Skills write files into the project and may change docs, config and tests after session reviews.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add plugins/claude-essentialsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Sub-agents read repository code, and executing-plans edits files and performs a local merge to main.
- Skills write files into the project and may change docs, config and tests after session reviews.
This is third-party code. Review the repository files before installing.
What it does
The plugin bundles the author's daily toolkit under a single `ce` namespace. The `ce:executing-plans` skill takes a plan or RFC through devil's-advocate review, implementation by groups of sub-agents, tests, code review and a local merge to main, and pushes only when asked. `ce:post-mortem` reviews one or many sessions and turns friction into changes to docs, config, skills and tests. The other skills cover writing voice and structure (`ce:writer` with ten personas, `ce:structuring-articles`), interface design, product planning, module architecture, tests, error handling, databases and Effect 4 code. Four sub-agents ship with it: `ce:code-reviewer`, `ce:devils-advocate`, `ce:copywriter` and `ce:log-reader`. Skills load from the request description and run by hand as `/ce:<name>`.
Who it is for. Developers on Claude Code or Codex who want a ready process from plan to merge plus reference skills for engineering practice.
Good fit when
- A plan or RFC is ready and has to pass design review, implementation, tests and code review in one run.
- After a long session you want a review that turns recurring friction into changes to rules and skills.
- README or article text reads like AI output and you want it rewritten in the voice of a specific role.
- Tests are flaky and you need a method that uses real dependencies and waits for async work.
Not a fit when
- You need deep specialization in one framework: most skills are general, and only Effect 4 has a deep reference.
- You want sub-agents in Codex: they work only in Claude Code, while Codex gets the skills.
- Your team already fixed its own rules in `.claude/rules/`: they override the skill defaults anyway.
Example request
Run this plan through the devil's advocate, implement it, run code review and merge to main locally.Limitations
The `ce` sub-agents work only in Claude Code, and Codex gets the skills alone. Opinionated skills defer to repository rules by default: `.claude/rules/` and `CLAUDE.md` take precedence, and the skills say so at the top. The `code-reviewer`, `devils-advocate` and `copywriter` agents are set to opus and `log-reader` to sonnet, so token use is noticeable. The `executing-plans` flow performs a local merge to main, so run it on a prepared branch. The plugin needs no settings of its own beyond a Claude Code version recent enough to support plugins.
How to disable. Run `/plugin uninstall ce` in Claude Code. In Codex, remove the plugin with Codex tooling.
FAQ
How do I install Claude Essentials in Claude Code?
Add the marketplace with `/plugin marketplace add https://github.com/rileyhilliard/claude-essentials`, then run `/plugin install ce`. The skills appear in the `ce` namespace.
Does the plugin work in Codex?
Yes, minus the sub-agents. `codex plugin marketplace add rileyhilliard/claude-essentials` and `codex plugin add ce@claude-essentials` install the skills from the same files.
What does ce:executing-plans do?
It takes a plan or RFC through devil's-advocate review, implementation by sub-agent groups, tests, code review and a local merge to main. It pushes only on explicit request.
How do I run a skill manually?
Type `/ce:<name>`, for example `/ce:post-mortem`. Usually nothing needs a manual call: a skill loads when the request matches its description.
How do I adapt the plugin to my repository?
Put rules in `.claude/rules/` and `CLAUDE.md`: they override skill defaults. Adding project skills and hooks on top of `ce` is described in `docs/extending-for-projects.md`.
Discussion
No questions or reviews yet.
Related
PluginsClaude Code plugins: plan, work and review commands, subagents, hooks and writing skills in a practical minimalism spirit.
A Claude Code plugin: 39 commands for PRs, review, commits and specs, nine expert roles and hooks, in eight language versions
A set of slash commands, skills and subagents for Claude Code: review, tests, security, releases, docs and GitHub to Linear sync
A plugin that turns Claude Code into a 16 agent team: documentation first planning, TDD and 9 pre-merge quality gates.
A set of 24 slash commands for the Claude Code CLI: commits, review, refactoring, tests and cleanup without repeating the same prompts
Nick Tune's plugin marketplace for Claude Code: checks before a task is handed in, code review and TDD personas
README in short
The README tables eleven skills and four sub-agents, gives install commands for Claude Code and Codex and shows which requests load which skill. It ends with how to extend `ce` with project rules.