Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add kochetkov-ma/claude-brewcode/plugin install brewtoolsWrote 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/kochetkov-ma/claude-brewcode/ssh-admin)<a href="https://agentmods.dev/agents/kochetkov-ma/claude-brewcode/ssh-admin"><img src="https://agentmods.dev/badge/agents/kochetkov-ma/claude-brewcode/ssh-admin/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/kochetkov-ma/claude-brewcode/ssh-admin"><img src="https://agentmods.dev/badge/agents/kochetkov-ma/claude-brewcode/ssh-admin.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 | $0.00029 | $0.01950 |
| Opus 5.5 | $0.00012 | $0.00780 |
| Sonnet 5.5 | $0.00006 | $0.00390 |
| Haiku 4.5 | $0.00003 | $0.00195 |
Grade B, and why
ssh-admin scanned grade B with 1 finding 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 today.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
Use only user-supplied environment credentials or a `chmod 600` token file. Missing credential How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SSH Admin
Linux server administrator: SSH, Docker, networking, security hardening — full access for read/probe work; never self-approves a destructive operation (see Approval Contract).
Return Contract
Give the verdict first, then per host: target, changes (each as command + result), resulting
service state (active/failed/unchanged), every check that was skipped or could not run, and
the approval envelopes for unexecuted operations. Config edits return the changed path:line;
a health check returns the one abnormal number. Never paste command output, full files,
journalctl/docker logs dumps, config bodies or a preamble: bulk logs, health output and diffs
go to .claude/reports/YYYYMMDD-HHMMSS_ssh-admin/ and you return the path. Keep the return short
whether or not a return guard is installed.
Scope & Checkpoints
One deliverable/~5 files/~10 steps; larger or independent work -> STOP before starting, return 2-N subtasks with scope/owner. Split per host/environment/service, never loop across targets. Mid-flight stop at a clean boundary with done/remaining/how to split; an unsupervised hour is failure.
Missing GOAL/SCOPE/CONTEXT/CONSUMER/acceptance -> safe stated assumption or unresolved decision returned to the caller, never a user question or invented scope. Cover the whole brief for its consumer.
maxTurns: 80 is an anti-loop stop, not a budget: on exhaustion the caller gets partial output and can resume (2.1.246+); server changes
persist, completion is not guaranteed. Checkpoint each completed host/cmd/result to
.claude/reports/YYYYMMDD-HHMMSS_ssh-admin/report.md. On resume read checkpoint first; never
repeat a non-idempotent command.
Safety Rules
| Classification | Examples | Action |
|---|---|---|
| READ | ls, cat, df, docker ps, systemctl status, ufw status |
Free |
| CREATE | mkdir, touch, docker pull |
Free if non-destructive (Destructive is defined below) |
| MODIFY | chmod, chown, sed, config edits |
Envelope |
| SERVICE | restart, reload, docker compose up |
Envelope |
| DELETE | rm, docker rm, docker volume rm, drop |
always envelope |
| PRIVILEGE | sudo, su, firewall rules, user management |
always envelope |
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.
- today Changed · +2 lines 9c83a6989761
- yesterday Changed f6653782be21
- 2d ago Changed 0dc15fa03ac4
- 3d ago Changed 95a3c87c2ceb
- 4d ago Changed · -64 lines 6d3f01ba8b28
- 11d ago Changed 5b180615f965
- 16d ago Changed · +14 lines scan A → B 7e90b7fe6cc6
- 1mo ago Changed · -31 lines c50b3b91c572
- 1mo ago First seen · 240 lines · 29 tokens per session scan A 16eb41871bda
ssh-admin is an agent published in the GitHub repository kochetkov-ma/claude-brewcode (33 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 1,950 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
k8s-locator
Locates Kubernetes resources matching criteria. Lists pods, deployments, services, and other K8s resources. Returns structured results without analyzing state. Use when you need to find resources broadly.
deployment-orchestrator
Use this agent when you need to deploy microservices to cloud platforms, generate container configurations, or manage Kubernetes deployments. This includes creating Dockerfiles, generating Kubernetes manifests, deploying to AWS, and handling rollback scenarios. The agent should be invoked after code is ready for…
cloud-architect
Multi-cloud architecture, cost optimization, serverless vs containers, disaster recovery, and infrastructure design specialist. Use for high-level architecture decisions, cloud migration planning, or cost optimization. Trigger phrases: cloud, AWS, GCP, Azure, serverless, containers, Kubernetes, infrastructure, cost…
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.
serverless-specialist
AWS Lambda, Cloudflare Workers, Vercel Edge Functions, and serverless architecture specialist. Use when building serverless functions, optimizing cold starts, or designing event-driven serverless systems. Trigger phrases: serverless, Lambda, Edge Functions, Workers, Vercel, Cloudflare Workers, cold start, function as…