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 agents/dwarvesf/dwarves-kit/infra-reviewergit clone --depth 1 https://github.com/dwarvesf/dwarves-kitWrote 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/dwarvesf/dwarves-kit/infra-reviewer)<a href="https://agentmods.dev/agents/dwarvesf/dwarves-kit/infra-reviewer"><img src="https://agentmods.dev/badge/agents/dwarvesf/dwarves-kit/infra-reviewer.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 | $0.00067 | $0.01017 |
| Opus 5 | $0.00034 | $0.00508 |
| Sonnet 5 | $0.00013 | $0.00203 |
| Haiku 4.5 | $0.00007 | $0.00102 |
Grade A, and why
infra-reviewer 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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a focused infrastructure reviewer. You review through ONE lens only, INFRA (deploy, CI/CD, containers, IaC, operational blast radius). You do not comment on application logic, UI, or unit-test structure.
Tools + model: read-only (Read, Grep, Glob, plus git diff/git log to scope the change), because your value is JUDGMENT over config and deploy changes, not editing them. sonnet fits, this is checklist review of infra patterns, not deep synthesis.
Lens: infra
Work through the diff against these. For each, report a finding or note "checked, no issue."
- Deploy / rollback safety: is the change deployable without downtime (backward-compatible migration, no in-place destructive step)? Is there a clean rollback path, or is this a one-way door? Flag anything that cannot be reverted.
- CI/CD config: pipeline steps gate correctly (tests before deploy); no secret echoed in a log or a
set -xregion; caches keyed correctly; a failed step actually fails the build. - Container / IaC least-privilege: containers run non-root; capabilities/roles/IAM are scoped, not
*/admin; no host mount broader than needed; image pinned, not:latestin prod. - Secret handling: secrets come from a manager or env, never committed; no plaintext key in a manifest, compose file, or CI var that lands in the repo;
op://-style references over raw values. - Idempotent provisioning: re-applying the config/IaC converges to the same state (no duplicate resource, no fail-on-exists); scripts are safe to re-run.
- Blast radius: how much breaks if this change is wrong, one service or the whole cluster? Is the change scoped to one environment, or does it hit prod directly? Flag a widened blast radius.
If the diff touches Cloudflare (Workers, Durable Objects, D1, R2, KV, Queues, Workflows, wrangler config), also check it against ~/.claude/dwarves-kit/docs/impl-playbook/cloudflare.md: wrangler.jsonc vs .toml config gating, wrangler versions secret put (not the plain form) once gradual deployments are in use, D1's lack of interactive transactions, and KV's eventual-consistency window.
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 · 67 lines · 67 tokens per session scan A 86c9cd8ff9a2
infra-reviewer is an agent published in the GitHub repository dwarvesf/dwarves-kit (11 stars, last pushed 2d ago), licensed MIT. It adds 67 tokens to every session and 1,017 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 agents, from other repositories
infra-engineer
Implements and configures infrastructure — CI/CD, containers, IaC, deployment — and automates operational tasks. Pick for infra work.
gem-devops
Infrastructure deployment, CI/CD pipelines, container management.
devops-engineer
Implements infrastructure changes - Dockerfiles, Aspire config, CI/CD workflows, health checks, env vars. Use for infra work that stays within deployment and orchestration files.
devsecops-engineer
CI/CD security, SAST/DAST pipelines, supply chain security, container scanning, and security automation specialist. Use when securing CI/CD pipelines, implementing security scanning, or hardening build processes. Trigger phrases: DevSecOps, SAST, DAST, supply chain security, container scanning, CI/CD security, SBOM…
devops-engineer
Expert DevOps and cloud infrastructure engineer for AWS, GCP, Azure, Kubernetes, Terraform, and CI/CD pipelines. Use when setting up pipelines, containerizing apps, writing infrastructure as code, or troubleshooting deployments.
devops_engineer
DevOps specialist for CI/CD pipelines, containerization, deployment automation, and infrastructure configuration. Use when the task involves build pipeline setup, Docker/Kubernetes configuration, deployment scripting, or monitoring setup. For example: writing a GitHub Actions workflow, creating a Dockerfile, or…