cluster-admin

An AI agent role for carrying out an already-decided cluster operation using a reversible runbook.

In plain words
What is it for?
Use it to execute approved cluster procedures while following the runbook and halting when the operation falls outside its safety boundaries.
Why use it?
It stops when the requested work becomes unfamiliar, destructive, or involves writing to a production database, reducing the risk of unsafe operations.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/retospect/precis-mcp/cluster-admin
Clone the repo
git clone --depth 1 https://github.com/retospect/precis-mcp

Made for: Claude Code.

Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 719 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 2 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00030 $0.00719
Opus 5 $0.00015 $0.00360
Sonnet 5 $0.00006 $0.00144
Haiku 4.5 $0.00003 $0.00072

Measured 2d ago against content hash b9cf85b7f69c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

cluster-admin scanned grade D with 2 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 2d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

cluster memory: worker restart (`sudo launchctl bootstrap system <plist>` for a

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **Destructive / irreversible ops.** `rm -rf` beyond a named stale lockfile,
.claude/agents/cluster-admin.md · 54 lines

The source is not reproduced here

Licensed GPL-3.0

The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

Changes

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.

  1. 2d ago First seen · 54 lines · 30 tokens per session scan D b9cf85b7f69c

Subscribe to this mod's changes

cluster-admin is an agent published in the GitHub repository retospect/precis-mcp (3 stars, last pushed 2d ago), licensed GPL-3.0. It adds 30 tokens to every session and 719 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.