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/getklai/klai/deploy-composenpx skills add GetKlai/klai --skill deploy-composegit clone --depth 1 https://github.com/GetKlai/klaiWhat 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 | $0.00069 | $0.00690 |
| Opus 5 | $0.00034 | $0.00345 |
| Sonnet 5 | $0.00014 | $0.00138 |
| Haiku 4.5 | $0.00007 | $0.00069 |
Grade A, and why
deploy-compose scanned grade A with 0 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 2d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploy flow (compose → core-01)
Two separate halves. Config is CI-synced; secrets are pushed manually.
Half 1 — config sync (automatic, CI)
.github/workflows/deploy-compose.yml runs on pushes to main that touch deploy/docker-compose.yml, deploy/docker-compose.override.yml, the listed core-01 config paths, deploy/scripts/**, its smoke test, or the workflow itself:
- Validates image tags + pullability (
deploy-image-checkskill) and LibreChat patch drift — a failure here stops the deploy before anything reaches the server. - SSH-syncs the compose file + configs to core-01 and runs
scripts/smoke-docker-socket-proxy.sh. That post-deploy smoke test currently warns on failure but is deliberately non-blocking.
For those exact core-01 paths, merging to main is the config deploy. Other code changes use their own service workflows.
GPU Compose — validation only
.github/workflows/validate-gpu-compose.yml validates deploy/docker-compose.gpu.yml on pull requests and pushes to main. It checks Compose syntax, pinned Vexa tags, and anonymous image pullability. It performs no SSH, sync, or deploy to gpu-01. Follow the relevant runbook and obtain explicit approval before any gpu-01 mutation.
Half 2 — secrets (manual, deploy.sh)
deploy/deploy.sh [service] handles the monorepo's secrets side only: it decrypts .sops env files locally (needs ~/.config/sops/age/keys.txt or $SOPS_AGE_KEY_FILE) and pipes them to the configured server over SSH. The compose file itself is version-controlled and contains no secrets. Use deploy/SECRETS_MATRIX.md for scope.
Servers
Topology, IPs, and access live in klai-infra/SERVERS.md — that file is the source of truth, don't duplicate it. Key facts: app services run on core-01; GPU services (incl. the locally-built transcription-service) run on gpu-01 and are reverse-tunneled to core-01 via autossh (/opt/klai/gpu-tunnel-key on core-01; core-01 reaches them at 172.18.0.1:<port>).
When a deploy did not land
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.
- 2d ago First seen · 39 lines · 69 tokens per session scan A 95aa7c2356cc
deploy-compose is a skill published in the GitHub repository GetKlai/klai (11 stars, last pushed 2d ago), licensed MIT. It adds 69 tokens to every session and 690 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
reproduce-issue
The single skill for reproducing an nx issue. Given a GitHub issue number (human entry) OR explicit repro parameters (agent entry), it runs the reproduction ENTIRELY inside an isolated Docker sandbox — gVisor on Linux, the Docker VM on macOS — so the untrusted repro's install scripts and commands never execute on the…
timoni
Use when deploying applications to Kubernetes with Timoni. Covers installing and upgrading module instances from OCI registries, composing multi-app deployments with bundles, injecting values from clusters or CI with runtimes, targeting multiple clusters, and authoring, testing, signing and publishing modules with CUE.
atmos-aws-ecr
AWS ECR commands in Atmos: atmos aws ecr login, ECR auth integrations, Docker credential writes, registry login via identity or explicit registry.
windows-builder
Build Windows images with Packer using WinRM communicator and PowerShell provisioners. Use when creating Windows AMIs, Azure images, or VMware templates.
release-openclaw-plugin-testing
Plan and run pre-release OpenClaw plugin validation across bundled plugins, package artifacts, lifecycle commands, doctor/fix, config round-trip, gateway startup, SDK compatibility, Docker E2E, Package Acceptance, and Testbox proof.