operator-command-lessons-learned

A project rule for recording what went wrong when operator commands fail and updating the related Compose operator rules in the same task. Compose is a tool for defining and running groups of containers.

In plain words
What is it for?
Use it when maintaining container operations, troubleshooting operator commands, and updating their working procedures.
Why use it?
It prevents the same failed command pattern from being repeated without documenting the fix.

Cursor rule

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 rules/tacc/hpcperfstats/operator-command-lessons-learned
Clone the repo
git clone --depth 1 https://github.com/TACC/HPCPerfStats
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 4,729 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00000 $0.04729
Opus 5 $0.00000 $0.02364
Sonnet 5 $0.00000 $0.00946
Haiku 4.5 $0.00000 $0.00473

Measured 2d ago against content hash 3ecced0701b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

operator-command-lessons-learned scanned grade C 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 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.

Recursive force deletehighDestructive command

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

- Binding only Let’s Encrypt **`live/`** or **`rm -rf`** on a symlink into it — can wipe live cert links (hpcperfstats04 2026-08-29); mount **`/etc/letsencrypt`** parent + optional **`HPCPERFSTATS_SSL_CERTS_REL`**.
hpcperfstats/cursor-rules/operator-command-lessons-learned.mdc · 103 lines

The source is not reproduced here

Licensed LGPL-2.1

The repository is licensed LGPL-2.1, 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 · 103 lines · 0 tokens per session scan C 3ecced0701b8

Subscribe to this mod's changes

operator-command-lessons-learned is a cursor rule published in the GitHub repository TACC/HPCPerfStats (58 stars, last pushed 2d ago), licensed LGPL-2.1. It costs nothing until one of its globs matches a file; then it loads 4,729 tokens. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.