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/dkurti/ha-mcp/agents-mdgit clone --depth 1 https://github.com/dkurti/HA-mcpWrote 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/dkurti/ha-mcp/agents-md)<a href="https://agentmods.dev/instructions/dkurti/ha-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/dkurti/ha-mcp/agents-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 | $0.07283 | $0.07283 |
| Opus 5 | $0.03642 | $0.03642 |
| Sonnet 5 | $0.01457 | $0.01457 |
| Haiku 4.5 | $0.00728 | $0.00728 |
Grade A, and why
HA-mcp AGENTS.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 3d 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 — 787 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code when working with this repository.
Repository Structure
This repository uses a worktree-based development workflow.
Documentation Setup:
- This file is
AGENTS.md(the canonical source) CLAUDE.mdis a symlink pointing toAGENTS.md- Read either file - they're the same content
- Commit changes to
AGENTS.md, the symlink will automatically reflect them
Directory Structure:
/home/julien/github/ha-mcp/ # Main repository (checkout master here)
├── AGENTS.md # This file (canonical source)
├── CLAUDE.md -> AGENTS.md # Symlink for convenience
├── worktree/ # Git worktrees (gitignored)
│ ├── issue-42/ # Feature branch worktree
│ └── fix-something/ # Fix branch worktree
├── local/ # Scratch work (gitignored)
└── .claude/agents/ # Custom agent workflows
Why use worktree/ subdirectory:
- Keeps worktrees organized in one place
- Gitignored (won't pollute
git status) - All worktrees automatically inherit
.claude/agents/workflows - Easy cleanup:
git worktree pruneremoves stale references
Worktree Workflow
Creating Worktrees
ALWAYS create worktrees in the worktree/ subdirectory, not at the repository root.
# Correct - worktrees go in worktree/ subdirectory
cd /home/julien/github/ha-mcp
git worktree add worktree/issue-42 -b issue-42
git worktree add worktree/feat-new-feature -b feat/new-feature
# Wrong - don't create worktrees at repo root
git worktree add issue-42 -b issue-42 # ❌ Creates orphaned worktree
git worktree add ../issue-42 -b issue-42 # ❌ Outside repo, no .claude/agents/
Working in a worktree:
# Navigate to your worktree
cd worktree/issue-42
# Work normally - you have full access to .claude/agents/
git status
git commit -m "feat: implement feature"
git push
# When done, return to main repo and clean up
cd /home/julien/github/ha-mcp
git worktree remove worktree/issue-42
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.
- 3d ago First seen · 787 lines · 7,283 tokens per session scan A 8bc383c4e201
HA-mcp AGENTS.md is an instructions file published in the GitHub repository dkurti/HA-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 7,283 tokens to every session, about $0.0364 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.