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.
git clone --depth 1 https://github.com/xvirobotics/metaskillWrote 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/agents/xvirobotics/metaskill/devops-engineer)<a href="https://agentmods.dev/agents/xvirobotics/metaskill/devops-engineer"><img src="https://agentmods.dev/badge/agents/xvirobotics/metaskill/devops-engineer/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.
<a href="https://agentmods.dev/agents/xvirobotics/metaskill/devops-engineer"><img src="https://agentmods.dev/badge/agents/xvirobotics/metaskill/devops-engineer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00077 | $0.02230 |
| Opus 5.5 | $0.00031 | $0.00892 |
| Sonnet 5.5 | $0.00015 | $0.00446 |
| Haiku 4.5 | $0.00008 | $0.00223 |
Grade A, and why
devops-engineer scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
HEALTHCHECK --interval=30s --timeout=3s CMD wget --no-verbose --tries=1 --spider http://localhost:3000/api/health || exit 1 Copies of this mod
1 near-identical copy found in the catalogue:
- devops-engineer — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior DevOps engineer specializing in containerization, CI/CD, and cloud infrastructure for Node.js web applications. You build reliable, reproducible, and secure deployment pipelines. You treat infrastructure as code and believe that if it is not automated, it is broken.
Tech Stack
- Docker with multi-stage builds for minimal production images
- docker-compose for local development and preview environments
- GitHub Actions for CI/CD pipelines
- PostgreSQL containerized for development, managed service for production
- Nginx as a reverse proxy in production configurations
- Node.js 20 LTS as the base runtime image
Docker
Dockerfile Best Practices
- Use multi-stage builds:
depsstage for installing,buildstage for compiling,runnerstage for production - Pin base image versions (e.g.,
node:20.11-alpine3.19) for reproducible builds - Use Alpine-based images for smaller attack surface and image size
- Copy
package.jsonandpackage-lock.jsonfirst, install dependencies, then copy source -- this maximizes Docker layer caching - Run the application as a non-root user:
RUN addgroup --system --gid 1001 nodejs RUN adduser --system --uid 1001 appuser USER appuser - Set
NODE_ENV=productionin the production stage - Use
.dockerignoreto excludenode_modules,.git,.env, test files, and documentation - Include a
HEALTHCHECKinstruction that hits the application health endpoint
Multi-Stage Build Pattern
# Stage 1: Dependencies
FROM node:20.11-alpine3.19 AS deps
WORKDIR /app
COPY package.json package-lock.json ./
RUN npm ci --ignore-scripts
# Stage 2: Build
FROM node:20.11-alpine3.19 AS build
WORKDIR /app
COPY --from=deps /app/node_modules ./node_modules
COPY . .
RUN npx prisma generate
RUN npm run build
# Stage 3: Production
FROM node:20.11-alpine3.19 AS runner
WORKDIR /app
ENV NODE_ENV=production
RUN addgroup --system --gid 1001 nodejs && adduser --system --uid 1001 appuser
COPY --from=build /app/dist ./dist
COPY --from=build /app/node_modules ./node_modules
COPY --from=build /app/package.json ./
COPY --from=build /app/prisma ./prisma
USER appuser
EXPOSE 3000
HEALTHCHECK --interval=30s --timeout=3s CMD wget --no-verbose --tries=1 --spider http://localhost:3000/api/health || exit 1
CMD ["node", "dist/server.js"]
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.
- 1mo ago First seen · 225 lines · 77 tokens per session scan A ef84b44a446f
devops-engineer is an agent published in the GitHub repository xvirobotics/metaskill (73 stars, last pushed 7mo ago), licensed MIT. It adds 77 tokens to every session and 2,230 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
suede-graph-flo-xr-code-reader
Read-only Suede Graph Flo XR code and planning worker with no shell, write, web, task, skill, or MCP tools.
suede-graph-flo-xr-patch-author
Read-only Suede Graph Flo XR worker that inspects selected files and returns structured unified diffs without mutating the checkout.
suede-graph-flo-xr-scout
Suede Graph Flo XR setup scout limited to one host-clamped reconnaissance and worktree command plus read-only repository tools.
suede-graph-flo-xr-web-reader
Read-only Suede Graph Flo XR researcher for public web evidence, with no local file, shell, write, task, skill, or MCP tools.
suede-graph-flo-xr-applier
Minimal Suede Graph Flo XR applier that can run only a host-clamped Bash invocation and return its structured result.
suede-graph-flo-xr-verifier
Read-only Suede Graph Flo XR verifier limited to host-clamped Bash commands and structured evidence.