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/giantswarm/musterWrote 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/rules/giantswarm/muster/zz_generated.go-llm-rules)<a href="https://agentmods.dev/rules/giantswarm/muster/zz_generated.go-llm-rules"><img src="https://agentmods.dev/badge/rules/giantswarm/muster/zz_generated.go-llm-rules/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/rules/giantswarm/muster/zz_generated.go-llm-rules"><img src="https://agentmods.dev/badge/rules/giantswarm/muster/zz_generated.go-llm-rules.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 | $0.00342 | $0.00342 |
| Opus 5.5 | $0.00137 | $0.00137 |
| Sonnet 5.5 | $0.00068 | $0.00068 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
zz_generated.go-llm-rules 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 2mo 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- zz_generated.go-llm-rules — 100% identical, 0 lines differ
- zz_generated.go-llm-rules — 100% identical, 0 lines differ
What it actually says
description: Go language-specific development guidelines and patterns globs: **/*.go,go.mod,go.sum
These guidelines apply to Go code and supplement any other general development instructions or workflows.
Go Code Guidelines
- All Go code is expected to adhere to the rules outlined in the Giant Swarm style guide located at @https://github.com/giantswarm/fmt/tree/main/go .
- Always fetch and fully understand the style guide before reviewing any code.
- The Giant Swarm style guide linked above must always be considered definitive. ALL rules and provisions contained in the style guide MUST be met.
- When applying the style guide, always list all instances of a particular issue, grouped by the finding type.
Formatting
CI will perform the following check for proper code formatting and sorting/grouping of imports:
go install golang.org/x/tools/cmd/goimports@latest && \
if [[ -n $(goimports -local github.com/${CIRCLE_PROJECT_USERNAME}/${CIRCLE_PROJECT_REPONAME} -l .) ]];
then
goimports -local github.com/${CIRCLE_PROJECT_USERNAME}/${CIRCLE_PROJECT_REPONAME} -d . && exit 1;
fi
When creating or modifying Go files, perform the according check and mitigate any issues before committing.
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.
- 2mo ago First seen · 36 lines · 342 tokens per session scan A bf099bfe1ede
zz_generated.go-llm-rules is a cursor rule published in the GitHub repository giantswarm/muster (40 stars, last pushed yesterday), licensed Apache-2.0. It adds 342 tokens to every session, about $0.0014 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.
zz_generated.go-llm-rules compared with cursor rules from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| zz_generated.go-llm-rulesgiantswarm/muster | Cursor rule | 40 | yesterday | Apache-2.0 | A | 342 | Cursor |
| gonavi-goSyngnat/GoNavi | Cursor rule | 2.1k | yesterday | Apache-2.0 | A | 0 | Cursor |
| backend0xJacky/nginx-ui | Cursor rule | 12k | yesterday | AGPL-3.0 | A | 441 | Cursor |
| code-stylecoddy-project/coddy-agent | Cursor rule | 199 | yesterday | MIT | A | 366 | Cursor |
| go-grpc-service-ruleholtwood/awesome-cursorrules-zh | Cursor rule | 241 | 18d ago | MIT | A | 140 | Cursor |
| 05-go-helpersclubpay/ronykit | Cursor rule | 38 | 5d ago | BSD-3-Clause | A | 450 | Cursor |
| gozapstore/zsp | Cursor rule | 19 | 3d ago | MIT | A | 0 | Cursor |