@simonjamesrowe/agent Setup

GitHub Actions

AI agent setup for the simonjamesrowe org: skills, instructions, MCP servers and plugins for Claude Code, Gemini CLI and Codex

Devops Developer Tools

Add to Cursor Add to VS Code Run on PlugMCP

GitHub npm Website

Add to Cursor Add to VS Code Run on PlugMCP

1{2  "mcpServers": {3    "simonjamesrowe-agent-setup": {4      "command": "npx",5      "args": [6        "-y",7        "@simonjamesrowe/[email protected]"8      ]9    }10  }11}

.cursor/mcp.jsonMCP server

Transport: stdio
Status: Local

Power your agent

Add this server

The publisher's own command. Not a PlugMCP endpoint.

Add to Cursor Add to VS Code Run on PlugMCP

Host a copy with our keys and logs.

Local command

npx -y @simonjamesrowe/[email protected]

Claude Code has no install link for a local command. Copy the command below and run it in a terminal.

shClaude Code

1claude mcp add simonjamesrowe-agent-setup -- npx -y @simonjamesrowe/agent-setup@1.7.0

Run in a terminal.

jsonClaude Desktop

1{2  "mcpServers": {3    "simonjamesrowe-agent-setup": {4      "command": "npx",5      "args": [6        "-y",7        "@simonjamesrowe/[email protected]"8      ]9    }10  }11}

claude_desktop_config.json

Local · npmPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport: stdio
Version: 1.7.0
Last checked: 2026-10-28

Stars: —
Tools: —
Uptime: —

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

How do I install @simonjamesrowe/agent Setup?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does @simonjamesrowe/agent Setup need an API key?

No required environment variable is listed on this record.

What transport does @simonjamesrowe/agent Setup use?

@simonjamesrowe/agent Setup runs locally over stdio.

When was @simonjamesrowe/agent Setup last checked?

Last checked 2026-10-28. AI agent setup for the simonjamesrowe org: skills, instructions, MCP servers and plugins for Claude Code, Gemini CLI and Codex

From the publisher

Documentation

agent-setup

One command that sets up three different coding agents with the same skills, instructions and tools for working on the simonjamesrowe org:

Claude Code (Anthropic) — ~/.claude/
Gemini CLI (Google) — ~/.gemini/
Codex (OpenAI) — ~/.codex/

Skills are authored once, in agent-agnostic markdown, and fanned out to each tool's native location — so switching agents doesn't mean starting from a blank slate. agent-setup also registers MCP servers and installs CLI plugins for whichever of the three it finds on your PATH.

What each agent gets

	Claude Code	Gemini CLI	Codex
Org skills (20)	✅ `~/.claude/skills/`	✅ `~/.gemini/skills/`	✅ `~/.codex/skills/`
Instructions	✅ `CLAUDE.md`	✅ `GEMINI.md`	✅ `AGENTS.md`
MCP servers	✅	✅	✅
`mattpocock-skills` (25 skills)	✅ plugin	✅ via `gemini skills install`	✅ plugin
`spring-tools` plugin	✅	❌ no plugin mechanism	❌ Claude-format only
speckit	✅	✅	✅ (tool-agnostic, via `uv`)
Moderne CLI + OpenRewrite MCP	✅	❌ not supported upstream	✅

Quick start

npx @simonjamesrowe/agent-setup

Check what's installed without changing anything:

npx @simonjamesrowe/agent-setup doctor

Flags

Flag	Description
`--yes`	no prompts, accept defaults
`--tools <a,b>`	limit to `claude,gemini,codex` (default: auto-detect)
`--skip <a,b>`	skip provisioners: `skills,instructions,mcp,plugins`
`--target <dir>`	override home directory (testing/CI); force-skips `mcp` and `plugins`, which exec real CLIs that mutate actual user config regardless of `--target`
`--with <a,b>`	opt in to optional components: `embabel-guide`

Commands: install (default), doctor (check-only), help.

Without --tools, agent-setup auto-detects which of claude, gemini and codex are on PATH and only provisions those.

What gets installed

Destinations

Tool	Skills directory	Instructions file
Claude Code	`~/.claude/skills/`	`~/.claude/CLAUDE.md`
Gemini CLI	`~/.gemini/skills/`	`~/.gemini/GEMINI.md`
Codex	`~/.codex/skills/`	`~/.codex/AGENTS.md`

Skills (components/skills/) are copied verbatim into each detected tool's skills directory.
Instructions (components/instructions/global.md) are merged into each tool's instructions file inside a marked block (``), so re-running install updates the block in place without disturbing anything you've added outside it. doctor reports the block as missing if it's absent or has been edited/clobbered.

Skills

Skill	What it's for
`backend-test`	Run and interpret simonrowe.dev backend tests, checkstyle and coverage.
`blog-publish`	Research, draft, illustrate, publish and verify first-party simonrowe.dev blog posts.
`chat-e2e-verify`	Browser-driven quality check of the simonrowe.dev chatbot against a local environment.
`code-review-triage`	Diagnose why the automated code reviewer did not review a pull request on simonrowe.dev.
`content-source-add`	Add a new content-aggregation source (blog/news/events scraper) to simonrowe.dev.
`demo-plan`	Grill Simon on a product demo's aim, audience and key messages, then draft a scene-by-scene script for approval.
`demo-record`	Build a narrated demo video from an approved script: Google Cloud TTS voice-over, full-viewport Playwright recording across sites, native macOS apps filmed with ScreenCaptureKit, hand-drawn Excalidraw diagram walkthroughs, ffmpeg mix to MP4 with captions.
`dependency-cve-fix`	Fix OWASP Dependency-Track CVE findings in simonrowe.dev by bumping the affected dependency, opening a PR, and driving CI to green.
`embabel-guide`	Run the Embabel docs MCP server (`embabel/guide`) locally and register it, for authoring Embabel agent code on the JVM.
`frontend-design`	Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one.
`langfuse-verify`	Verify Langfuse LLM trace plumbing for simonrowe.dev end to end.
`honeycomb-verify`	Verify fresh deployed traces and privacy fields through Playwright MCP.
`local-env`	Start, stop and verify the simonrowe.dev local development environment.
`mongock-migration`	Create a Mongock change unit for simonrowe.dev data changes with the repo's idempotency and test patterns.
`prod-backup-ops`	Trigger, verify and manage simonrowe.dev production backups to Google Drive.
`prod-data-restore`	Restore the latest simonrowe.dev production backup (Google Drive) into a local environment via the admin Data Ops UI.
`prod-deploy`	Deploy simonrowe.dev to production: merge, watch the Publish workflow, restart on the Pi, smoke-test.
`prod-logs`	Fetch simonrowe.dev production logs from Grafana Cloud Loki, Portainer, or docker compose.
`pr-review-loop`	Drive a pull request from ready-to-review to all-signals-green: CI, the reviewer bot and SonarQube Cloud, triaged in a bounded loop.
`prod-triage`	Runbook for simonrowe.dev being down or misbehaving in production.
`spring-boot-upgrade`	Upgrade the simonrowe.dev backend across Spring Boot versions with OpenRewrite, via the Moderne MCP server or the OpenRewrite Gradle plugin.

See docs/SKILLS.md for naming conventions, where a new skill should live, the SKILL.md format contract, and the checklist for adding one.

MCP servers

Registered at user scope for every detected agent.

Server	Transport	Auth	What it's for
`playwright`	stdio (`npx @playwright/mcp@latest`)	none	Browser automation — admin UI flows, chat verification
`excalidraw`	HTTP	none	Diagrams
`javadocs`	HTTP (`javadocs.dev`)	none	Java/Kotlin/Scala API docs from Maven Central
`linear`	HTTP (`mcp.linear.app`)	OAuth (interactive, first use)	Linear issues, projects and comments
`simonrowe-dev`	HTTP (`api.simonrowe.dev/mcp`)	none	The site's own content — profile, jobs, skills, blogs, news, events, code examples
`honeycomb`	HTTP	OAuth	Application traces — opt-in with `--with honeycomb`
`amplitude`	HTTP	OAuth	Product analytics — opt-in with `--with amplitude`
`embabel-guide`	stdio (`mcp-remote` → `localhost:1337`)	your own LLM key	Embabel framework docs — opt-in, see below
`moderne`	stdio (local, via the `mod` CLI)	none for today's recipes	OpenRewrite recipe search and deterministic execution

playwright, excalidraw, javadocs, linear, simonrowe-dev and embabel-guide, honeycomb and amplitude are agent-setup's own catalog (MCP_SERVERS in lib/provisioners/mcp.js). moderne is not in that array — it's registered by the mod CLI itself (mod config agent-tools <agent> install, see CLI tools below), not by agent-setup's MCP provisioner.

simonrowe-dev is the site's own MCP server, served by the Spring Boot backend at https://api.simonrowe.dev/mcp (streamable HTTP, no auth, no local process — it is up whenever the API is). It gives every agent first-hand access to the live site content instead of guessing: getProfile, getJobs, getSkills, searchBlogs, getRecentBlogs, searchNews, getUpcomingEvents, getCodeExamples, searchSite and submitContactForm. The last of those emails Simon and is the only side-effecting tool; the server rate-limits it to once per session itself.

A server already registered at project or local scope would shadow the user-scope one, so that's reported as failed with the mcp remove command to fix it rather than being silently overwritten.

linear, honeycomb and amplitude use interactive OAuth, so registration and authorization are separate steps: install registers it, then you sign in once yourself, with your agent's own command:

Agent	Sign in with
Claude Code	`/mcp`, in an interactive session
Codex	`codex mcp login linear`
Gemini CLI	`/mcp auth linear`, in an interactive session

(Verified 2026-08-25: codex mcp login --help on codex-cli 0.133.0, and gemini-cli 0.49.0's own docs/tools/mcp-server.md, which documents /mcp auth serverName. Gemini has no gemini mcp login subcommand.)

Until you do, doctor reports the row as optional — registered but not authorized — rather than unchanged, because the server is configured but its tools do not work. That row never affects the exit code, since the sign-in is a browser flow agent-setup cannot perform for you. Auth state is only detected for Claude Code: claude mcp get prints a Status: line that says so, Gemini's check reads ~/.gemini/settings.json (which carries no auth metadata at all), and Codex's unauthorized output is still unverified.

Honeycomb and Amplitude

Install either or both with agent-setup install --with honeycomb,amplitude. The same authorization commands above apply, replacing linear with the server name. Signing into the website with Google does not itself authorize an MCP client.

The catalog defaults to US. For an EU account, remove and re-add the server using its regional URL before signing in:

Server	US	EU
Honeycomb	`https://mcp.honeycomb.io/mcp`	`https://mcp.eu1.honeycomb.io/mcp`
Amplitude	`https://mcp.amplitude.com/mcp`	`https://mcp.eu.amplitude.com/mcp`

For example: codex mcp remove honeycomb, then codex mcp add honeycomb --url https://mcp.eu1.honeycomb.io/mcp. Existing registrations are matched by name, so subsequent installs preserve this override. Claude Code uses mcp remove <name> -s user and mcp add --scope user --transport http <name> <url>.

Honeycomb MCP is included in Free; enable Team Intelligence and authorize only mcp:read for investigation (codex mcp login honeycomb --scopes mcp:read). Its ingest key is a separate server-side credential and cannot authorize MCP queries. For Amplitude, request read-only access with codex mcp login amplitude --scopes all:read,offline_access (verified against the hosted US OAuth server). Amplitude OAuth also inherits the user's project permissions; use a role with MCP read access and no write access if appropriate. Service-account authentication requires Enterprise, so it is not part of this Free-tier setup. Neither integration ships tokens. Verify a read-only tool call after login; registration alone is not proof of access.

Sources: Honeycomb MCP and Amplitude MCP.

Read-only Linear

If you would rather agents never write to your tracker, remove the server and re-add it against Linear's read-only endpoint — same server, search and read only:

claude mcp remove linear -s user
claude mcp add --scope user --transport http linear https://mcp.linear.app/mcp/readonly

--scope user is not optional: claude mcp add defaults to local scope (claude mcp add --help, Claude Code 2.1.220, 2026-08-25), and a local-scope linear shadows the user-scope one — which agent-setup reports as failed. Use the equivalent remove/add pair for Codex or Gemini.

The swap survives future upgrades because agent-setup's registration check matches on the server name only, never on the URL: execBasedCheck in lib/provisioners/mcp.js looks for the name in mcp get output, and the Gemini check looks for the mcpServers key. So a readonly-swapped linear reports unchanged on every later install run and is never clobbered. Editing the URL inside the installed npm package would not survive the next global install; this does.

CLI tools and plugins

Tool	Installed via	Agents
`mattpocock-skills`	`plugin marketplace add mattpocock/skills` + `plugin install`/`plugin add` (Claude, Codex); `gemini skills install` (Gemini)	all three
`spring-tools`	`claude plugin marketplace add` + `plugin install`	Claude Code
`speckit`	`uv tool install specify-cli`	all (tool-agnostic)
`moderne`	`brew install moderneinc/moderne/mod` + `mod config agent-tools <agent> install` (once per supported agent)	Claude Code, Codex

`mattpocock-skills` — the process layer

mattpocock/skills (MIT) replaced superpowers in 1.0.0. It carries 25 skills: grill-me/grilling (a design-tree interview that stress-tests a plan before any code is written), tdd, code-review, diagnosing-bugs, domain-modeling, to-spec, to-tickets, research, handoff and more.

Installed from upstream rather than vendored into components/skills/, so it tracks the source instead of drifting from a frozen copy.

Reaching all three agents takes two different mechanisms, because only two of them have a plugin system:

Agent	Mechanism
Claude Code	`claude plugin marketplace add mattpocock/skills` + `claude plugin install mattpocock-skills@mattpocock`
Codex	`codex plugin marketplace add mattpocock/skills` + `codex plugin add mattpocock-skills@mattpocock`
Gemini CLI	`gemini skills install https://github.com/mattpocock/skills --path skills/engineering` (and `--path skills/productivity`)

Codex reads Claude-format marketplaces. Verified 2026-09-06 on codex-cli 0.150.1: codex plugin marketplace add mattpocock/skills resolves the repo's .claude-plugin/marketplace.json and registers the marketplace as mattpocock (the marketplace name comes from that file, not from the repo name — the two differ here). The install verb is plugin add, not plugin install, and Codex has no plugin enable.

Gemini has no plugin mechanism at all, but gemini skills install <git-url> --path <subdir> clones a repo once and installs every SKILL.md beneath one subdirectory. The two paths are skills/engineering and skills/productivity rather than skills — the repo also carries skills/in-progress (8) and skills/misc (4), which the upstream plugin manifest deliberately excludes. These land in ~/.gemini/skills/ alongside this repo's own 20 skills; there is no name collision today, and neither set clobbers the other.

grill-me is invisible to the model, by design. It ships disable-model-invocation: true, so Claude and Codex both hide it from the model's skill list and only surface it when you type it. The model-visible half is grilling, which carries the actual interview loop. grill-me is a one-line entry point that calls it.

`superpowers` is removed, not just unmanaged

superpowers was installed by this tool for Claude Code up to 0.4.1, and OpenAI's own openai-curated marketplace offers it to Codex as well. From 1.0.0 install actively uninstalls it from both: an orphaned superpowers keeps injecting its SessionStart block into every session, which is the standing context cost this change exists to remove.

doctor reports a still-installed superpowers as missing — the one place that status means "present, and should not be" — so a machine that has not run the migration exits non-zero. This is a one-release migration and will be dropped once every machine has run 1.x.

mod config agent-tools <agent> install registers the Moderne MCP server and installs Moderne's own OpenRewrite skills for that agent, so agent-setup calls it once per supported agent (claude, codex) rather than reimplementing either step. It deliberately never runs the blanket mod config agent-tools install — that form provisions all eight agents Moderne supports regardless of which ones agent-setup was asked to provision, and it writes .github/instructions/ and .vscode/mcp.json into whatever directory it happens to be run from. Gemini CLI is not a supported target for mod config agent-tools upstream and is reported as skipped.

Recipes resolve from Maven Central today, so mod needs no credential to run the current Spring Boot upgrade recipe. A Code Genome Project token only matters once you need a recipe release newer than Central carries — the one-time setup for that is in the spring-boot-upgrade skill.

Optional components

Not installed by default; opt in by name.

npx @simonjamesrowe/agent-setup --with embabel-guide

Component	Why it's opt-in
`embabel-guide`	Needs a local Docker + Neo4j server on `localhost:1337` and your own LLM API key. Registering it unconditionally would leave a dead server configured on every machine.

doctor reports opted-out components as optional, never missing, so they don't affect its exit code.

Platform support: macOS and Linux. Windows is untested — tool detection shells out to which.

Updating

Re-run the same command to pick up new skills, instructions or plugin versions — install is idempotent and only touches what's changed:

npx @simonjamesrowe/agent-setup

Version policy

patch — wording or fix (skill body edit, instructions tweak, bug fix)
minor — new skill or new flag (backward-compatible addition)
major — rename or removal (a skill, flag or destination changes shape or disappears)

Development

git clone [email protected]:simonjamesrowe/agent-setup.git
cd agent-setup
npm test
npm run lint:skills

Smoke-test an install into a disposable target directory instead of your real home directory:

node bin/agent-setup.js install --yes --target "$(mktemp -d)" --tools claude,gemini,codex --skip mcp,plugins

License

MIT — see LICENSE.

@simonjamesrowe/agent Setup

GitHub Actions

AI agent setup for the simonjamesrowe org: skills, instructions, MCP servers and plugins for Claude Code, Gemini CLI and Codex

Devops Developer Tools

Add to Cursor Add to VS Code Run on PlugMCP

GitHub npm Website

Add to Cursor Add to VS Code Run on PlugMCP

1{2  "mcpServers": {3    "simonjamesrowe-agent-setup": {4      "command": "npx",5      "args": [6        "-y",7        "@simonjamesrowe/[email protected]"8      ]9    }10  }11}

.cursor/mcp.jsonMCP server

Transport: stdio
Status: Local

Power your agent

Add this server

The publisher's own command. Not a PlugMCP endpoint.

Add to Cursor Add to VS Code Run on PlugMCP

Host a copy with our keys and logs.

Local command

npx -y @simonjamesrowe/[email protected]

Claude Code has no install link for a local command. Copy the command below and run it in a terminal.

shClaude Code

1claude mcp add simonjamesrowe-agent-setup -- npx -y @simonjamesrowe/agent-setup@1.7.0

Run in a terminal.

jsonClaude Desktop

1{2  "mcpServers": {3    "simonjamesrowe-agent-setup": {4      "command": "npx",5      "args": [6        "-y",7        "@simonjamesrowe/[email protected]"8      ]9    }10  }11}

claude_desktop_config.json

Local · npmPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport: stdio
Version: 1.7.0
Last checked: 2026-10-28

Stars: —
Tools: —
Uptime: —

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

How do I install @simonjamesrowe/agent Setup?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does @simonjamesrowe/agent Setup need an API key?

No required environment variable is listed on this record.

What transport does @simonjamesrowe/agent Setup use?

@simonjamesrowe/agent Setup runs locally over stdio.

When was @simonjamesrowe/agent Setup last checked?

Last checked 2026-10-28. AI agent setup for the simonjamesrowe org: skills, instructions, MCP servers and plugins for Claude Code, Gemini CLI and Codex

From the publisher

Documentation

agent-setup

One command that sets up three different coding agents with the same skills, instructions and tools for working on the simonjamesrowe org:

Claude Code (Anthropic) — ~/.claude/
Gemini CLI (Google) — ~/.gemini/
Codex (OpenAI) — ~/.codex/

What each agent gets

	Claude Code	Gemini CLI	Codex
Org skills (20)	✅ `~/.claude/skills/`	✅ `~/.gemini/skills/`	✅ `~/.codex/skills/`
Instructions	✅ `CLAUDE.md`	✅ `GEMINI.md`	✅ `AGENTS.md`
MCP servers	✅	✅	✅
`mattpocock-skills` (25 skills)	✅ plugin	✅ via `gemini skills install`	✅ plugin
`spring-tools` plugin	✅	❌ no plugin mechanism	❌ Claude-format only
speckit	✅	✅	✅ (tool-agnostic, via `uv`)
Moderne CLI + OpenRewrite MCP	✅	❌ not supported upstream	✅

Quick start

npx @simonjamesrowe/agent-setup

Check what's installed without changing anything:

npx @simonjamesrowe/agent-setup doctor

Flags

Flag	Description
`--yes`	no prompts, accept defaults
`--tools <a,b>`	limit to `claude,gemini,codex` (default: auto-detect)
`--skip <a,b>`	skip provisioners: `skills,instructions,mcp,plugins`
`--target <dir>`	override home directory (testing/CI); force-skips `mcp` and `plugins`, which exec real CLIs that mutate actual user config regardless of `--target`
`--with <a,b>`	opt in to optional components: `embabel-guide`

Commands: install (default), doctor (check-only), help.

Without --tools, agent-setup auto-detects which of claude, gemini and codex are on PATH and only provisions those.

What gets installed

Destinations

Tool	Skills directory	Instructions file
Claude Code	`~/.claude/skills/`	`~/.claude/CLAUDE.md`
Gemini CLI	`~/.gemini/skills/`	`~/.gemini/GEMINI.md`
Codex	`~/.codex/skills/`	`~/.codex/AGENTS.md`

Skills (components/skills/) are copied verbatim into each detected tool's skills directory.
Instructions (components/instructions/global.md) are merged into each tool's instructions file inside a marked block (``), so re-running install updates the block in place without disturbing anything you've added outside it. doctor reports the block as missing if it's absent or has been edited/clobbered.

Skills

Skill	What it's for
`backend-test`	Run and interpret simonrowe.dev backend tests, checkstyle and coverage.
`blog-publish`	Research, draft, illustrate, publish and verify first-party simonrowe.dev blog posts.
`chat-e2e-verify`	Browser-driven quality check of the simonrowe.dev chatbot against a local environment.
`code-review-triage`	Diagnose why the automated code reviewer did not review a pull request on simonrowe.dev.
`content-source-add`	Add a new content-aggregation source (blog/news/events scraper) to simonrowe.dev.
`demo-plan`	Grill Simon on a product demo's aim, audience and key messages, then draft a scene-by-scene script for approval.
`demo-record`	Build a narrated demo video from an approved script: Google Cloud TTS voice-over, full-viewport Playwright recording across sites, native macOS apps filmed with ScreenCaptureKit, hand-drawn Excalidraw diagram walkthroughs, ffmpeg mix to MP4 with captions.
`dependency-cve-fix`	Fix OWASP Dependency-Track CVE findings in simonrowe.dev by bumping the affected dependency, opening a PR, and driving CI to green.
`embabel-guide`	Run the Embabel docs MCP server (`embabel/guide`) locally and register it, for authoring Embabel agent code on the JVM.
`frontend-design`	Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one.
`langfuse-verify`	Verify Langfuse LLM trace plumbing for simonrowe.dev end to end.
`honeycomb-verify`	Verify fresh deployed traces and privacy fields through Playwright MCP.
`local-env`	Start, stop and verify the simonrowe.dev local development environment.
`mongock-migration`	Create a Mongock change unit for simonrowe.dev data changes with the repo's idempotency and test patterns.
`prod-backup-ops`	Trigger, verify and manage simonrowe.dev production backups to Google Drive.
`prod-data-restore`	Restore the latest simonrowe.dev production backup (Google Drive) into a local environment via the admin Data Ops UI.
`prod-deploy`	Deploy simonrowe.dev to production: merge, watch the Publish workflow, restart on the Pi, smoke-test.
`prod-logs`	Fetch simonrowe.dev production logs from Grafana Cloud Loki, Portainer, or docker compose.
`pr-review-loop`	Drive a pull request from ready-to-review to all-signals-green: CI, the reviewer bot and SonarQube Cloud, triaged in a bounded loop.
`prod-triage`	Runbook for simonrowe.dev being down or misbehaving in production.
`spring-boot-upgrade`	Upgrade the simonrowe.dev backend across Spring Boot versions with OpenRewrite, via the Moderne MCP server or the OpenRewrite Gradle plugin.

See docs/SKILLS.md for naming conventions, where a new skill should live, the SKILL.md format contract, and the checklist for adding one.

MCP servers

Registered at user scope for every detected agent.

Server	Transport	Auth	What it's for
`playwright`	stdio (`npx @playwright/mcp@latest`)	none	Browser automation — admin UI flows, chat verification
`excalidraw`	HTTP	none	Diagrams
`javadocs`	HTTP (`javadocs.dev`)	none	Java/Kotlin/Scala API docs from Maven Central
`linear`	HTTP (`mcp.linear.app`)	OAuth (interactive, first use)	Linear issues, projects and comments
`simonrowe-dev`	HTTP (`api.simonrowe.dev/mcp`)	none	The site's own content — profile, jobs, skills, blogs, news, events, code examples
`honeycomb`	HTTP	OAuth	Application traces — opt-in with `--with honeycomb`
`amplitude`	HTTP	OAuth	Product analytics — opt-in with `--with amplitude`
`embabel-guide`	stdio (`mcp-remote` → `localhost:1337`)	your own LLM key	Embabel framework docs — opt-in, see below
`moderne`	stdio (local, via the `mod` CLI)	none for today's recipes	OpenRewrite recipe search and deterministic execution

A server already registered at project or local scope would shadow the user-scope one, so that's reported as failed with the mcp remove command to fix it rather than being silently overwritten.

Agent	Sign in with
Claude Code	`/mcp`, in an interactive session
Codex	`codex mcp login linear`
Gemini CLI	`/mcp auth linear`, in an interactive session

Honeycomb and Amplitude

The catalog defaults to US. For an EU account, remove and re-add the server using its regional URL before signing in:

Server	US	EU
Honeycomb	`https://mcp.honeycomb.io/mcp`	`https://mcp.eu1.honeycomb.io/mcp`
Amplitude	`https://mcp.amplitude.com/mcp`	`https://mcp.eu.amplitude.com/mcp`

Sources: Honeycomb MCP and Amplitude MCP.

Read-only Linear

If you would rather agents never write to your tracker, remove the server and re-add it against Linear's read-only endpoint — same server, search and read only:

claude mcp remove linear -s user
claude mcp add --scope user --transport http linear https://mcp.linear.app/mcp/readonly

CLI tools and plugins

Tool	Installed via	Agents
`mattpocock-skills`	`plugin marketplace add mattpocock/skills` + `plugin install`/`plugin add` (Claude, Codex); `gemini skills install` (Gemini)	all three
`spring-tools`	`claude plugin marketplace add` + `plugin install`	Claude Code
`speckit`	`uv tool install specify-cli`	all (tool-agnostic)
`moderne`	`brew install moderneinc/moderne/mod` + `mod config agent-tools <agent> install` (once per supported agent)	Claude Code, Codex

`mattpocock-skills` — the process layer

Installed from upstream rather than vendored into components/skills/, so it tracks the source instead of drifting from a frozen copy.

Reaching all three agents takes two different mechanisms, because only two of them have a plugin system:

Agent	Mechanism
Claude Code	`claude plugin marketplace add mattpocock/skills` + `claude plugin install mattpocock-skills@mattpocock`
Codex	`codex plugin marketplace add mattpocock/skills` + `codex plugin add mattpocock-skills@mattpocock`
Gemini CLI	`gemini skills install https://github.com/mattpocock/skills --path skills/engineering` (and `--path skills/productivity`)

`superpowers` is removed, not just unmanaged

Optional components

Not installed by default; opt in by name.

npx @simonjamesrowe/agent-setup --with embabel-guide

Component	Why it's opt-in
`embabel-guide`	Needs a local Docker + Neo4j server on `localhost:1337` and your own LLM API key. Registering it unconditionally would leave a dead server configured on every machine.

doctor reports opted-out components as optional, never missing, so they don't affect its exit code.

Platform support: macOS and Linux. Windows is untested — tool detection shells out to which.

Updating

Re-run the same command to pick up new skills, instructions or plugin versions — install is idempotent and only touches what's changed:

npx @simonjamesrowe/agent-setup

Version policy

patch — wording or fix (skill body edit, instructions tweak, bug fix)
minor — new skill or new flag (backward-compatible addition)
major — rename or removal (a skill, flag or destination changes shape or disappears)

Development

git clone [email protected]:simonjamesrowe/agent-setup.git
cd agent-setup
npm test
npm run lint:skills

Smoke-test an install into a disposable target directory instead of your real home directory:

node bin/agent-setup.js install --yes --target "$(mktemp -d)" --tools claude,gemini,codex --skip mcp,plugins

License

MIT — see LICENSE.

Add this server

Host a copy with our keys and logs.

Server facts

Tools

Questions

How do I install @simonjamesrowe/agent Setup?

Does @simonjamesrowe/agent Setup need an API key?

What transport does @simonjamesrowe/agent Setup use?

When was @simonjamesrowe/agent Setup last checked?

Documentation

agent-setup

What each agent gets

Quick start

Flags

What gets installed

Destinations

Skills

MCP servers

Honeycomb and Amplitude

Read-only Linear

CLI tools and plugins

mattpocock-skills — the process layer

superpowers is removed, not just unmanaged

Optional components

Updating

Version policy

Development

License

Add this server

Host a copy with our keys and logs.

Server facts

Tools

Questions

How do I install @simonjamesrowe/agent Setup?

Does @simonjamesrowe/agent Setup need an API key?

What transport does @simonjamesrowe/agent Setup use?

When was @simonjamesrowe/agent Setup last checked?

Documentation

agent-setup

What each agent gets

Quick start

Flags

What gets installed

Destinations

Skills

MCP servers

Honeycomb and Amplitude

Read-only Linear

CLI tools and plugins

mattpocock-skills — the process layer

superpowers is removed, not just unmanaged

Optional components

Updating

Version policy

Development

License

`mattpocock-skills` — the process layer

`superpowers` is removed, not just unmanaged

`mattpocock-skills` — the process layer

`superpowers` is removed, not just unmanaged