pluggedin-app: Skill for Claude Code

.claude/skills/pluggedin-stack-ops/SKILL.md

pluggedin-stack-ops is a skill for Claude Code from VeriTeknik/pluggedin-app. It costs 61 tokens per session (1,299 once invoked), scanned B, original, MIT.

A runbook for operating the plugged.in production application, which runs as a group of connected Docker containers. It covers deployment, health checks, logs, routing, and rollback-related problems.

In plain words
What is it for?
Use it to deploy, restart, verify, inspect, or roll back the containerized production stack and investigate application or Traefik routing failures.
Why use it?
It prevents operational mistakes such as deploying without required secrets or configuration and helps diagnose 404 and 5xx errors after changes.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is VeriTeknik/pluggedin-app's own configuration. It tells Claude Code how to work on pluggedin-app itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pluggedin-app configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/pluggedin/crontab.pre-ofelia.backup.

Reuse

Borrowing it

Nothing to install: this file belongs to VeriTeknik/pluggedin-app. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/VeriTeknik/pluggedin-app/main/.claude/skills/pluggedin-stack-ops/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/VeriTeknik/pluggedin-app

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pluggedin-stack-ops

README.md
[![agentmods](https://agentmods.dev/badge/skills/veriteknik/pluggedin-app/pluggedin-stack-ops/github.svg)](https://agentmods.dev/skills/veriteknik/pluggedin-app/pluggedin-stack-ops)
Your own site
<a href="https://agentmods.dev/skills/veriteknik/pluggedin-app/pluggedin-stack-ops"><img src="https://agentmods.dev/badge/skills/veriteknik/pluggedin-app/pluggedin-stack-ops/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pluggedin-stack-ops

Your own site · 80×15
<a href="https://agentmods.dev/skills/veriteknik/pluggedin-app/pluggedin-stack-ops"><img src="https://agentmods.dev/badge/skills/veriteknik/pluggedin-app/pluggedin-stack-ops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,299 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00061 $0.01299
Opus 5.5 $0.00024 $0.00520
Sonnet 5.5 $0.00012 $0.00260
Haiku 4.5 $0.00006 $0.00130

Measured 2mo ago against content hash c0b32e60ec79, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

pluggedin-stack-ops scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo systemctl enable --now nginx pluggedin

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -o /dev/null -w '%{http_code}\n' https://plugged.in/
.claude/skills/pluggedin-stack-ops/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Operating the plugged.in production stack

plugged.in runs as a Docker Compose stack: Traefik on :80/:443, the Next.js app, Postgres 16 + pgvector, Redis, Ofelia (cron), and a docker-socket-proxy. The native nginx + systemd stack it replaced is stopped and disabled but still installed.

Entry point is always infra/scripts/deploy.sh. Running compose by hand skips secret decryption, so the secrets file and the staged Traefik config never appear.

Quick reference

Task Command
Deploy ./infra/scripts/deploy.sh
Smoke test ./infra/scripts/verify.sh (add --quick to skip the RAG canary)
Logs docker compose -f infra/docker-compose.yml logs -f --tail=50 pluggedin-app traefik
Which routers exist Traefik dashboard at https://traefik.plugged.in/api/http/routers (basic auth)

Health must report "status":"healthy" and "database":true. The endpoint never emits "ok" — asserting that is a bug that once made the smoke test unpassable.

Deploying is not just git pull

git pull alone can 404 the site.

infra/traefik/dynamic/ is bind-mounted straight from the git working tree, and Traefik hot-watches it. Any git operation that rewrites those files — pull, checkout, rebase — can be observed mid-write. Traefik then loads a file missing a middleware, every router referencing it errors, and the site returns 404 until the next reload. Observed for ~40s after a git checkout where the before and after content were identical: content equality is not write atomicity.

Until the dynamic config is staged outside the working tree, treat any git operation against this checkout as a change window: run it, then immediately check

curl -s -o /dev/null -w '%{http_code}\n' https://plugged.in/
docker logs --since 2m traefik 2>&1 | grep -i 'does not exist'

middleware "X@file" does not exist is the signature. It self-heals on the next reload; touch infra/traefik/dynamic/middlewares.yml forces one.

Read the full file on GitHub · 99 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 99 lines · 61 tokens per session scan B c0b32e60ec79

Subscribe to this mod's changes

pluggedin-stack-ops is a skill published in the GitHub repository VeriTeknik/pluggedin-app (102 stars, last pushed 4d ago), licensed MIT. It adds 61 tokens to every session and 1,299 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

pluggedin-stack-ops compared with skills from other repositories

pluggedin-stack-ops next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pluggedin-stack-opsVeriTeknik/pluggedin-appSkill1024d agoMITB61Claude Code
releasedylanroscover/EmbodySkill212yesterdayMITA63Claude Code
git-workflowmodelcontextprotocol/typescript-sdkSkill14kyesterdaynoneA10Claude Code, Codex
merge-divergent-toxdylanroscover/EmbodySkill212yesterdayMITA74Claude Code
opik-evaluatecomet-ml/opik-mcpSkill2259d agoApache-2.0A192Claude Code
polish-docs-metacyanheads/git-mcp-serverSkill2451mo agoApache-2.0A53Claude Code, Codex
report-issuecyanheads/git-mcp-serverSkill2451mo agoApache-2.0A51Claude Code, Codex