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 skills add chipi/agentic-ai-homelab --skill compose-checkgit clone --depth 1 https://github.com/chipi/agentic-ai-homelabWrote 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/chipi/agentic-ai-homelab/compose-check)<a href="https://agentmods.dev/skills/chipi/agentic-ai-homelab/compose-check"><img src="https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/compose-check/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/skills/chipi/agentic-ai-homelab/compose-check"><img src="https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/compose-check.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 | $0.00075 | $0.00769 |
| Opus 5.5 | $0.00030 | $0.00308 |
| Sonnet 5.5 | $0.00015 | $0.00154 |
| Haiku 4.5 | $0.00007 | $0.00077 |
Grade A, and why
compose-check 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 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.
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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
compose-check
Catch a broken compose stack before docker compose up, not after. Validates
syntax, interpolation, and env wiring — strictly read-only. This skill never
runs up, down, pull, or anything that mutates a stack or shared state.
When this applies
Editing a docker-compose*.yml / compose.ya?ml, or about to deploy one, or
asked to "check / validate the compose stack." Cheap; run it whenever in doubt.
Check each stack
- Find stacks —
docker-compose.yml,docker-compose.*.yml,compose.yml,compose.yaml(skip dated backups like*.yml.<date>). If none, say so. - Validate structure, then classify — for each file:
A fresh checkout usually has nodocker compose -f <file> config -q.env(gitignored, present only on the deploy host), so separate "not ready" from "broken":- exit 0 → structure + interpolation valid → PASS
- fails only with
env file ... not found→ the YAML is fine, the stack just needs an.envabsent from this checkout → ENV-MISSING (warn, name the exact path). Not a defect. - any other error (YAML parse,
additional property, bad interpolation,required variable is missing) → FAIL — surface the message.
- Undefined interpolation — grep for
${VAR}used without a default or required marker (${VAR:-default}/${VAR:?msg}). Any bare${VAR}not set in the environment or an.envbecomes an empty string at runtime. List them. - Env readiness — collect every
.envpath the stacks declare (top-level--env-file, serviceenv_file:) and report which exist vs are missing. When a stack is ENV-MISSING and a sibling.env.exampleexists, the fix iscp .env.example .env(then fill secrets) — say that explicitly.
Report
- Show full command output; end with one line per stack:
COMPOSE CHECK <stack>: PASS | ENV-MISSING | FAIL. - On FAIL, name the defect (the YAML error or the undefined
${VAR}), not just the exit code. On ENV-MISSING, name the.envto create and the.env.exampleto copy from.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 58 lines · 75 tokens per session scan A ee67012ce719
compose-check is a skill published in the GitHub repository chipi/agentic-ai-homelab (3 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 769 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
agent-sandbox
Agent skill for sandbox - invoke with $agent-sandbox.
github-actions-templates
Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications. Use when setting up CI/CD with GitHub Actions, automating development workflows, or creating reusable workflow templates.
cdf-orchestration-setup
Use when the user asks to deploy, install, reinstall, redeploy, upgrade, or connect to the CDF Orchestration Airflow controller. Owns the end-to-end deploy sequence and runs the cdf-orchestration-preflight audit first. Covers make setup, controller image builds, Helm installation, controller connection…
aiq-deploy
Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.
dynamo-recipe-runner
Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use router-starter for router-only mode work and troubleshoot for broken deployments.
kermt-monitor
Check progress for a detached KERMT run (pretrain, finetune, or any kermtrundetached invocation). Reads run.json, queries docker for container state, tails the pretrain/finetune log, and parses progress lines (epoch, step, val loss).