Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/veriteknik/pluggedin-app/pluggedin-stack-opsnpx skills add VeriTeknik/pluggedin-app --skill pluggedin-stack-opsgit clone --depth 1 https://github.com/VeriTeknik/pluggedin-appWrote 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.
[](https://agentmods.dev/skills/veriteknik/pluggedin-app/pluggedin-stack-ops)<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="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00061 | $0.01299 |
| Opus 5 | $0.00030 | $0.00649 |
| Sonnet 5 | $0.00012 | $0.00260 |
| Haiku 4.5 | $0.00006 | $0.00130 |
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 5d 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/ 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 pullalone 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.
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.
- 5d ago First seen · 99 lines · 61 tokens per session scan B c0b32e60ec79
pluggedin-stack-ops is a skill published in the GitHub repository VeriTeknik/pluggedin-app (99 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 1,299 once invoked, about $0.0003 per session on Opus 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.
Other skills, from other repositories
opik-evaluate
Build an LLM evaluation and run it against your app, returning an experiment with scores. Covers datasets, LLM judges, RAG evaluation, synthetic data, error analysis, and validating evaluators against human labels. Use when the user wants to measure or improve AI product quality, or asks about evals, judges, or…
local-rag-search
Efficiently perform web searches using the mcp-local-rag server with semantic similarity ranking. Use this skill when you need to search the web for current information, research topics across multiple sources, or gather context from the internet without using external APIs. This skill teaches effective use of…
algorand-interaction
Interact with Algorand blockchain via the Algorand MCP server — wallet operations, ALGO/ASA transactions, smart contracts, account info, NFD lookups, atomic groups, Tinyman swaps, Haystack Router best-price swaps, Alpha Arcade prediction markets, Pera asset verification, TEAL compilation, knowledge base. Use when user…
alpha-arcade-interaction
Trade on Alpha Arcade prediction markets on Algorand — browse markets, read orderbooks, place limit/market orders, manage positions, cancel/amend orders, split/merge shares, and claim winnings. Use when user asks about prediction markets, event betting, YES/NO shares, orderbooks, or Alpha Arcade.
haystack-router-interaction
Route and execute optimal token swaps on Algorand using Haystack Router via Algorand MCP tools. Use when getting best-price quotes across multiple Algorand DEXes and LST protocols, executing atomic swaps, and checking asset opt-in — all through the Algorand MCP server.
algorand-x402-payment
Execute x402 payments at runtime using Algorand MCP tools. Use whenever an HTTP request returns 402 Payment Required (or a PAYMENT-REQUIRED header), the user needs to access a paid API or x402-protected resource, or the user mentions x402, micropayments, paying for an endpoint, or "payment required" — even if they…