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.
npx agentmods add instructions/standardbeagle/brummer/claude-mdgit clone --depth 1 https://github.com/standardbeagle/brummerWhat 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 | $0.02082 | $0.02082 |
| Opus 5 | $0.01041 | $0.01041 |
| Sonnet 5 | $0.00416 | $0.00416 |
| Haiku 4.5 | $0.00208 | $0.00208 |
Grade B, and why
brummer CLAUDE.md 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 yesterday.
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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
brum 'node server.js' # Run arbitrary command The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- yesterday First seen · 184 lines · 2,082 tokens per session scan B 8415cbc4d71f
brummer CLAUDE.md is an instructions file published in the GitHub repository standardbeagle/brummer (0 stars, last pushed 1mo ago), with no licence file. It adds 2,082 tokens to every session, about $0.0104 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
bg-tasks-mcp AGENTS.md
AGENTS.md instructions for rookie136/bg-tasks-mcp, covering agents.md, bg-tasks background task management, available tools, available resources and usage patterns.
SaneProcess copilot-instructions.md
Instructions for sane-apps/SaneProcess, covering saneprocess - github copilot instructions, project overview, source of truth, code structure and rules for changes.
SaneProcess AGENTS.md
Instructions for sane-apps/SaneProcess, covering saneapps agents, what belongs here, session start, session end and core rules.
taskctl AGENTS.md
AGENTS.md instructions for taskctl/taskctl, covering agents.md, what this is, general, commands and architecture.
taskctl CLAUDE.md
Claude Code instructions for taskctl/taskctl, a project described as: Concurrent task runner, developer's routine tasks automation toolkit. Simple modern alternative to GNU Make 🧰.
localhost-mcp CLAUDE.md
Instructions for HasanJahidul/localhost-mcp, covering localhost-mcp — project context, status, architecture, mcp tools and safety.