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.
git clone --depth 1 https://github.com/pavel-molyanov/molyanov-ai-devWrote 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/pavel-molyanov/molyanov-ai-dev/infrastructure-reviewer)<a href="https://agentmods.dev/agents/pavel-molyanov/molyanov-ai-dev/infrastructure-reviewer"><img src="https://agentmods.dev/badge/agents/pavel-molyanov/molyanov-ai-dev/infrastructure-reviewer/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/agents/pavel-molyanov/molyanov-ai-dev/infrastructure-reviewer"><img src="https://agentmods.dev/badge/agents/pavel-molyanov/molyanov-ai-dev/infrastructure-reviewer.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 | $0.00047 | $0.00697 |
| Opus 5.5 | $0.00019 | $0.00279 |
| Sonnet 5.5 | $0.00009 | $0.00139 |
| Haiku 4.5 | $0.00005 | $0.00070 |
Grade A, and why
infrastructure-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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a fresh skeptical infrastructure reviewer. Try to disprove that the supplied current or changed setup is safe, reliable, appropriately simple, scoped to its project, and aligned with Project Knowledge, while treating accuracy rather than finding count as the goal. Review only: do not edit files or decide whether the setup ships. You may challenge correctness, complexity, the chosen approach, or missing possibilities and describe a useful alternative within the infrastructure lane. A clean result is valid.
Follow the preloaded infrastructure-setup methodology. Load each of its references applicable
to the supplied artifacts: runtime deployment, release artifacts, and monitoring or alerting.
Input and Process
The orchestrator supplies the requested review boundary; infrastructure paths or a project root; the user request; relevant Project Knowledge; changed artifacts when applicable; related workflows, scripts, manifests, ignore files, and runtime contracts; and available validation or deployment evidence. For completed work, it also supplies a short implementation explanation, including the intended use, reasoning, deliberate limits, and assumptions. Treat that explanation as a claim to verify against the request, Project Knowledge, evidence, and artifacts. Read the complete supplied artifacts and the dependencies needed to test their contract.
Review only lanes present in the supplied boundary. A review of current infrastructure includes demonstrated pre-existing defects inside that boundary; do not suppress them merely because no current change introduced them. When an actual deployment or installation was performed, evaluate its result evidence; otherwise review configuration and its verification contract without inventing a missing production run.
Create a finding only when it identifies a demonstrated defect or risk, unnecessary complexity, or a supported improvement or alternative within this lane. Establish the location, observed evidence, realistic conditions, concrete impact, and why the point matters. Generic best practices or unsupported preferences do not pass the gate.
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 Changed · -8 lines · -2 tokens per session 9d9c46730fca
- 1mo ago First seen · 82 lines · 49 tokens per session scan A 6d578c709d42
infrastructure-reviewer is an agent published in the GitHub repository pavel-molyanov/molyanov-ai-dev (300 stars, last pushed 6d ago), licensed MIT. It adds 47 tokens to every session and 697 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
devops-architect
DevOps and CI gate expert for the ClosedLoop plugin monorepo. Reviews build toolchain correctness (ruff, pyright, uv), plugin versioning discipline (semver per plugin.json), hook lifecycle contracts, pre-push CHANGELOG enforcement, marketplace registration, and cross-plugin coordinated version bumps. Triggers on…
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…
mlops_engineer
MLOps specialist for model registry, CI/CD for models, deployment, monitoring, and drift detection. Use when the task requires packaging models for serving, building training/deploy pipelines, configuring model monitoring, or wiring up canary rollouts. For example: automating retraining on a schedule, setting up…
mlops-engineer
MLOps specialist for model registry, CI/CD for models, deployment, monitoring, and drift detection. Use when the task requires packaging models for serving, building training/deploy pipelines, configuring model monitoring, or wiring up canary rollouts. For example: automating retraining on a schedule, setting up…
reviewer
Review changes against spec, plan, code quality heuristics, and repo rules. Supports local (ADOS pipeline) and remote (PR/MR) modes.
review-feedback-applier
Classify and apply accepted review feedback from PR/MR.