# Skills, MCP servers or plugins: which one, and where each lives

URL: https://developertoolkit.ai/en/ecosystem/
Description: Choose between AGENTS.md, a skill, a slash command, a subagent, a hook, an MCP server and a plugin, then find the ecosystem shelf that covers each one.

A coding agent has seven extension points: `AGENTS.md` (standing rules), skills (procedures loaded on demand), slash commands (procedures a person triggers), subagents (isolated side tasks), hooks (checks that always run), MCP servers (live external systems) and plugins (bundles of the rest). Choose by job, then measure context cost.

A colleague asks the agent to open a PR "the way we do it here". The agent has three sources of instructions, two GitHub integrations and a forgotten hook, and it follows the wrong one. This page helps developers and tech leads decide where a rule or tool belongs.

## Which mechanism does this job?

| Mechanism | Enters context | Reach for it when | Not for | Canonical page |
| --- | --- | --- | --- | --- |
| `AGENTS.md` (`CLAUDE.md`, Cursor Rules) | Every session, in full | build and test commands, rules for every task | long procedures, API docs | [Repository context files](/en/developer-scorecard-guide/claude-md-context/) |
| Skill (`SKILL.md` folder) | Name and description always, body when it fires | a repeatable procedure: TDD, a release checklist | credentials, live data | [Agent skills](/en/ecosystem/skills/) |
| Slash command (in Claude Code, a skill with `disable-model-invocation: true`) | Only when a person types it | steps that must never start alone: a deploy, a release cut | anything the agent should pick up unprompted | [Custom commands and skills](/en/claude-code/automate/custom-commands/) |
| Subagent | Its own window; only a summary returns | noisy searches, a second-opinion review | work that needs the main thread's context | [Custom subagents](/en/claude-code/automate/custom-subagents/) |
| Hook | Nothing, unless it returns output | rules that must hold every time: format on edit, block a secret | advice the model may weigh | [Hooks](/en/claude-code/automate/hooks-automation/) |
| MCP server | Tool schemas plus every result | reading or changing external state: PRs, tickets, a browser | conventions and style | [MCP servers](/en/ecosystem/mcp/) |
| Plugin (a versioned bundle of the above) | Whatever it bundles | a vendor's skills and server together, or a team's standard setup | a rule one line in `AGENTS.md` covers | [Plugins](/en/ecosystem/plugins/) |

The test: **a skill tells the agent how, an MCP server lets it act, and a hook makes sure it did.** A rule the agent may ignore belongs in `AGENTS.md` or a skill; a rule it must never break belongs in a hook or in CI.

Claude Code reads `CLAUDE.md` and falls back to `AGENTS.md` (v2.1.277 and later, both release channels on 2026-10-12). Codex skips `AGENTS.md` in an untrusted project (0.150.0 and later). In Claude Code, custom commands are skills, so Claude can invoke one on its own unless its frontmatter sets `disable-model-invocation: true`.

## Where each layer lives in the ecosystem

- [Skills](/en/ecosystem/skills/) — Practice skills, vendor skills by stack, installing and securing them.
- [MCP servers](/en/ecosystem/mcp/) — GitHub, Context7, Playwright and servers by job, plus token cost.
- [Plugins](/en/ecosystem/plugins/) — Install commands per agent, top plugins, team marketplaces.
- [Frameworks](/en/ecosystem/frameworks/) — Superpowers, Spec Kit, OpenSpec, BMAD and GSD, shipped as plugins.
- [Agent tools](/en/ecosystem/agent-tools/) — herdr, desktop environments, sandboxes, model gateways.
- [Observability and quality](/en/ecosystem/observability/) — Telemetry, cost, review bots, security gates, evals.
- [Models](/en/ecosystem/models/) — Current model names, prices and defaults.

## What changed in 2026

- **Plugins became the default install route.** On 2026-09-26, `claude-plugins-official` listed 314 plugins, `openai-curated` 65 and `cursor/plugins` 94.
- **Context cost became the selection criterion.** `claude plugin details` (Claude Code 2.1.283, 2026-09-26): about 838 tokens per session for `superpowers`, 41,515 for Everything Claude Code.
- **Churn is high.** GSD is now `@opengsd/gsd-core`; `openai/skills` gave way to `openai/plugins`.

## Equip one repo from zero

1. Record the baseline: `/context` in Claude Code. Codex and Cursor have no verified equivalent, so count servers with `codex mcp list` and skills with `npx skills list`. `claude plugin details <name>` prints any plugin's projected token cost, even for skills you install elsewhere.

2. Install one discipline pack. Matt Pocock's skills cover grilling, specs, tickets, TDD and review.

   **Claude Code**

   ```bash
   claude plugin install mattpocock-skills@claude-plugins-official --scope project
   claude plugin details mattpocock-skills
   ```

   **Codex**

   ```bash
   npx skills add mattpocock/skills --skill grill-me grilling setup-matt-pocock-skills -a codex
   ```

   **Cursor**

   ```bash
   npx skills add mattpocock/skills --skill grill-me grilling setup-matt-pocock-skills -a cursor
   ```

   `grill-me` is a one-line delegate that fails without `grilling`. Write `--skill grill-me`, never `--skill=grill-me`, which `skills` 1.7.0 drops silently. Plugin skills are namespaced: `/mattpocock-skills:grill-me` in Claude Code; an `npx skills` copy is `/grill-me` in Cursor and `$grill-me` in Codex.

3. Add GitHub and Context7. Read a fine-grained, single-repository token from a secret store (macOS Keychain here), never paste it. The [GitHub MCP page](/en/ecosystem/mcp/github-mcp/) lists minimum scopes and the `/readonly` URL.

   **Claude Code**

   ```bash
   export GITHUB_PERSONAL_ACCESS_TOKEN="$(security find-generic-password -s gh-mcp -w)"
   claude plugin install github@claude-plugins-official --scope project
   claude mcp add --transport http --scope project context7 https://mcp.context7.com/mcp
   ```

   **Codex**

   ```bash
   export GITHUB_PAT_TOKEN="$(security find-generic-password -s gh-mcp -w)"
   codex mcp add github --url https://api.githubcopilot.com/mcp/ --bearer-token-env-var GITHUB_PAT_TOKEN
   codex mcp add context7 --url https://mcp.context7.com/mcp
   ```

   **Cursor**

   Add Context7 to `.cursor/mcp.json`:

   ```json
   { "mcpServers": { "context7": { "url": "https://mcp.context7.com/mcp" } } }
   ```
   For GitHub in Cursor, follow the token setup on the [GitHub MCP page](/en/ecosystem/mcp/github-mcp/).

4. Measure again in a new session. If the cost outweighs the value, remove something.

5. Commit `.claude/settings.json`, `.mcp.json` and `.cursor/mcp.json` so the team gets the same setup through review. `codex mcp add` writes to your user config, so each Codex user repeats step 3. Each teammate still exports their own `GITHUB_PERSONAL_ACCESS_TOKEN` (the plugin reads exactly that name); tokens never go into the committed files.

**Copy-paste prompt: audit this repo's agent setup**

```text
List every source of instructions and tools this session has: AGENTS.md or CLAUDE.md files, installed skills and plugins, subagents, hooks and connected MCP servers. For each, give its location and what it costs in context. Then flag: (1) any rule that appears in two places, (2) any skill installed twice (plugin and npx skills), (3) any MCP server that duplicates a CLI already on PATH, such as gh, (4) any "must" rule that lives only in prose and should be a hook or a CI check. Propose removals first, additions last. Do not change any file.
```

## How you know the setup works without reading every line

- **Context budget:** the step 1 and step 4 numbers, recorded in the PR; see [reducing MCP token cost](/en/ecosystem/mcp/reducing-mcp-token-cost/).
- **Deterministic gates:** tests, type checks and a Gitleaks pre-commit hook.
- **A second model:** `codex review` or a review bot; see [agent PR review](/en/workflows/ship/agent-pr-review/).
- **Sign-off:** the tech lead reviews MCP and plugin changes as dependencies.

## When a layered setup goes wrong

| Symptom | Cause | Recovery |
| --- | --- | --- |
| Every skill appears twice | Installed as a plugin and with `npx skills` | Keep one route |
| The agent ignores a "must" rule | The rule lives only in prose | Move it into a hook or a CI check |
| An MCP result asks the agent to do something odd | Prompt injection through fetched content | Use read-only scopes; see [MCP security](/en/ecosystem/mcp/mcp-security/) |

## Where to go next from the ecosystem overview

- Before this: [Git worktrees for parallel agents](/en/developer-scorecard-guide/git-worktrees/), the previous step in the developer track.
- [Plugins and marketplaces](/en/ecosystem/plugins/) to pin versions per agent.
- [Agentic development frameworks compared](/en/ecosystem/frameworks/) to choose one discipline pack; [discipline packs](/en/ecosystem/frameworks/discipline-packs/) walks one feature from grilling to verification.
- [Model routing by evidence](/en/developer-scorecard-guide/model-routing/), the next step in the developer track.
