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/safetymp/autonomous-ehs-management/devops-srenpx skills add SafetyMP/Autonomous-EHS-Management --skill devops-sregit clone --depth 1 https://github.com/SafetyMP/Autonomous-EHS-ManagementWhat 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 | $0.00097 | $0.01498 |
| Opus 5 | $0.00048 | $0.00749 |
| Sonnet 5 | $0.00019 | $0.00300 |
| Haiku 4.5 | $0.00010 | $0.00150 |
Grade A, and why
devops-sre 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 3d 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.
| Wiring comments for metrics/logging/OTel | Ad-hoc `curl` to production without secrets hygiene | How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevOps / SRE (infrastructure & reliability)
Act as DevOps / SRE for this codebase: automate delivery, keep environments reproducible, and protect the merge bar. Do not implement tRPC routes, RBAC rules, Drizzle entities, or UX unless a production incident fix requires it.
Standards (2026)
- Immutable infrastructure — Declare desired state with Dockerfiles, Kubernetes YAML/Helm, Terraform/Pulumi, or the repo’s Vercel config. No one-off SSH “snowflakes.”
- CI/CD — Enforce lint → typecheck → unit tests before
main; smoke E2E as already defined in the handbook. Branch protection + required checks where org policy allows. - FinOps — Prefer scale-to-zero when idle (serverless, KEDA
ScaledObject, or managed options). Plain HPA cannot scale to 0; document when HA/min replicas override cost savings. - Secrets — Never commit real credentials. Runtime env only; use External Secrets / sealed secrets / cloud secret managers in cluster docs.
This repository (sources of truth)
| Topic | Location |
|---|---|
| Merge verification | AGENTS.md — npm run verify, npm run verify:all |
| CI workflow | .github/workflows/ci.yml |
| Runtime env contract | src/lib/env.ts |
| Vercel project config (cron, etc.) | vercel.ts |
| Next build / headers | next.config.ts |
| Production-oriented container image | Dockerfile (standalone output) |
| Kubernetes manifests (Kustomize) | deploy/k8s/ |
| AWS EKS + VPC (Terraform starter) | infra/terraform/ |
| GHCR publish on main | CI job publish in .github/workflows/ci.yml |
| Production promotion (Vercel + EKS) | .github/workflows/cd-promote-production.yml (REPO_SETUP.md) |
| Cursor IDE MCP (optional; not a deploy plane) | docs/cursor-tool-connections-deployment.md — inspect/Vercel/Neon helpers only; previews need migrations + cron rules below |
| Local app + Postgres (Compose) | docker-compose.yml; env template .env.docker.example |
| Local/demo Postgres (pgvector) | docker-compose.demo.yml; devcontainer .devcontainer/ |
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.
- 3d ago First seen · 74 lines · 97 tokens per session scan A b32293ded090
devops-sre is a skill published in the GitHub repository SafetyMP/Autonomous-EHS-Management (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 97 tokens to every session and 1,498 once invoked, about $0.0005 per session on Opus 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 2026-08-31.
Other skills, from other repositories
openshell-cli
Guide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration and refresh, policy iteration, settings, service exposure, BYOC workflows, and inference routing. Covers basic through advanced multi-step workflows. Trigger keywords - openshell, sandbox…
cloud-k8s
Use for authorized cloud, container, and Kubernetes security assessment including metadata SSRF, IAM misconfig, container escape paths, and cluster RBAC review.
kubernetes-specialist
Use when deploying or managing Kubernetes workloads. Invoke to create deployment manifests, configure pod security policies, set up service accounts, define network isolation rules, debug pod crashes, analyze resource limits, inspect container logs, or right-size workloads. Use for Helm charts, RBAC policies…
langbot-deploy
Deploy and configure a LangBot instance — Docker / Docker Compose, Kubernetes, the config.yaml model, the Box sandbox runtime, the plugin runtime, and the global API key. Use when installing, deploying, upgrading, or configuring LangBot in production or self-hosted environments. Triggers on "deploy langbot", "langbot…
doca-container-deployment
Use this skill when the user is hands-on deploying an in-bundle DOCA service container (Argus, DMS, Firefly, or UROM service) on a BlueField — kubelet standalone watching a static-pod manifests directory, YAML pod-spec drop, kubelet status / ENTRYPOINT logs / per-service liveness, smoke-before-bulk, and the layered…
compute-env-setup
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.