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/yarlson/yarstack/infra-reviewnpx skills add yarlson/yarstack --skill infra-reviewgit clone --depth 1 https://github.com/yarlson/yarstackWrote 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/yarlson/yarstack/infra-review)<a href="https://agentmods.dev/skills/yarlson/yarstack/infra-review"><img src="https://agentmods.dev/badge/skills/yarlson/yarstack/infra-review.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 | $0.00043 | $0.00338 |
| Opus 5 | $0.00022 | $0.00169 |
| Sonnet 5 | $0.00009 | $0.00068 |
| Haiku 4.5 | $0.00004 | $0.00034 |
Grade A, and why
infra-review 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 6d 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.
What it actually says
Infrastructure Review
Own pre-deployment infrastructure blast-radius analysis using non-mutating evidence.
Workflow
- Confirm the comparison target, source-to-rendered path, tooling, and affected environment using safe redacted identifiers.
- Rank changed resources by blast radius and inspect full definitions and dependency ordering.
- Check targeting, replacement or destruction, state and migration safety, data protection, partial-apply recovery, availability, disruption, capacity, and material cost.
- Verify provider or tool semantics from local versions or authoritative sources before claiming replacement or destruction.
- Run only trusted repository-supported non-mutating plan, render, diff, or dry-run checks when authorized.
- Delegate exploit analysis to
security-review, dependency provenance todependency-review, CI mechanics toci-review, and cross-cutting runtime readiness torollout-readiness-review.
Report severity, exact location, redacted environment reference, concrete blast radius, failure path, smallest correction, evidence, and uncertainty. Describe confirmed public exposure, privilege escalation, secret leakage, unprotected destruction, unsafe state migration, or missing recovery as blocking findings; do not claim authority to block an operation.
Never apply, deploy, install, upgrade, delete, destroy, or modify cloud state. Do not expose sensitive plan output or add policy frameworks merely for the review.
Finish with findings or no-findings, scope, destructive effects, cost impact, checks, and confidence limits.
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.
- 6d ago First seen · 24 lines · 43 tokens per session scan A e685e08cbcff
infra-review is a skill published in the GitHub repository yarlson/yarstack (3 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 338 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
mcore-run-on-slurm
How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDADEVICEMAXCONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-rank failure diagnosis.
deploy-to-vercel
Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".
doca-setup
Use this skill when the user is dealing with the DOCA environment around their workload — verifying an install is healthy, preparing the build env (pkg-config, headers, LDLIBRARYPATH, hugepages, devlink, representors), debugging env-class failures, deciding container-vs-bare-metal deployment shape, or reaching a DOCA…
aws-step-functions
Build workflows with AWS Step Functions state machines using the JSONata query language. Covers Amazon States Language (ASL) structure, state types, variables, data transformation, error handling, AWS service integration, and migrating from the JSONPath to the JSONata query language.
memstack-deployment-domain-ssl
Use this skill when the user says 'setup domain', 'configure DNS', 'SSL certificate', 'domain-ssl', 'custom domain', 'HTTPS setup', or needs to configure DNS records, SSL certificates, and custom domains for any hosting provider. Do NOT use for full deployment workflows.