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/higangssh/homebutler/claude-mdgit clone --depth 1 https://github.com/Higangssh/homebutlerWrote 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/instructions/higangssh/homebutler/claude-md)<a href="https://agentmods.dev/instructions/higangssh/homebutler/claude-md"><img src="https://agentmods.dev/badge/instructions/higangssh/homebutler/claude-md.svg" alt="Measured on agentmods" 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 | $0.00628 | $0.00628 |
| Opus 5 | $0.00314 | $0.00314 |
| Sonnet 5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
homebutler CLAUDE.md 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
homebutler
A single Go binary for running a small home server: CLI, TUI, web dashboard, and an MCP server, with no daemon and no database.
Verify before claiming anything works
gofmt -w .
go vet ./...
golangci-lint run
go test ./...
go build ./...
All five must pass. go test ./... takes several minutes — internal/network
and internal/remote wait on real timeouts — so start it early rather than
running it last.
Writing commits, PRs, and comments
Everything written here is read by users, contributors, and future maintainers.
Match the voice already in git log and CHANGELOG.md.
No tool attribution
Never add Co-Authored-By: Claude, Generated with Claude Code, 🤖 badges,
"AI-assisted" notes, or any other tool signature to a commit message, PR
description, issue comment, review comment, or code comment. The author is the
person who decided the change should exist.
Commit subjects
Conventional Commits (feat:, fix:, docs:, refactor:, test:, chore:),
lowercase after the type, no trailing period, no emoji.
Describe the behaviour that changed, not the mechanism. A fix: subject should
read as the symptom a user would have hit:
fix: watch check called systemd and pm2 targets clean without checking them
fix: don't blame the host key when the TOFU connection fails
feat: cap incident history so the watch directory stops growing forever
docs: lead the README with what homebutler actually prints
Not fix: update watch.go, and not fix: add nil check in checkTarget.
Commit bodies
Only when the subject cannot carry it. Explain why the change is correct or what breaks without it — the diff already shows what changed. A one-line commit with a good subject is finished, not lazy.
Note user-visible behaviour changes explicitly. Someone upgrading needs to know that settings which were silently inert will now take effect.
PR descriptions and comments
Lead with what changed and why it matters. Keep the implementation notes to the decisions a reviewer could not infer from the diff — what you reused, what you deliberately left alone, what fails fast and where.
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.
- 6d ago First seen · 74 lines · 628 tokens per session scan A 4360033e7f3f
homebutler CLAUDE.md is an instructions file published in the GitHub repository Higangssh/homebutler (268 stars, last pushed yesterday), licensed MIT. It adds 628 tokens to every session, about $0.0031 per session on Opus 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.
Other instructions, from other repositories
ollama AGENTS.md
AGENTS.md instructions for ollama/ollama, covering agents.md and building.
awesome-go AGENTS.md
AGENTS.md instructions for avelino/awesome-go, covering awesome-go · llm contribution guide, project snapshot, when modifying the awesome list, coding guidelines and testing & validation.
go-micro CLAUDE.md
Claude Code instructions for micro/go-micro, covering claude.md - go micro project guide, project overview, build & test, run all tests and run tests for a specific package.
ollama CLAUDE.md
Claude Code instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.
azure-sdk-for-go AGENTS.md
AGENTS.md instructions for Azure/azure-sdk-for-go, covering agents.md, repository overview, key documentation, go version support and agent capabilities and boundaries.
azure-sdk-for-go go-examples.instructions.md
Instructions for Azure/azure-sdk-for-go, a project described as: This repository is for active development of the Azure SDK for Go. For consumers of the SDK we recommend visiting our public developer docs at.