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/moellere/wirestudio/claude-mdgit clone --depth 1 https://github.com/moellere/WireStudioWrote 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/moellere/wirestudio/claude-md)<a href="https://agentmods.dev/instructions/moellere/wirestudio/claude-md"><img src="https://agentmods.dev/badge/instructions/moellere/wirestudio/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 | $0.00511 | $0.00511 |
| Opus 5 | $0.00255 | $0.00255 |
| Sonnet 5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
WireStudio 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 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — working conventions
Notes for Claude (and humans) when editing this repo.
Voice
- Concise. No marketing language, no emojis in code, comments, commits, PRs.
- Prefer plain prose over headers in short replies.
- State decisions and tradeoffs directly. Don't hedge.
Code
- Default to no comments. Add one only when the why is non-obvious (hidden constraint, workaround, surprising invariant).
- No "added for X" / "used by Y" comments. That belongs in commit messages.
- No backwards-compat shims, dead-code stubs, or unused-arg renames. Delete it.
- No premature abstraction. Three similar lines beat a wrong helper.
- Validate at boundaries (file load, CLI input, future API). Trust internal callers.
Architecture
design.jsonis the single source of truth. Generators are pure functions ofdesign.json+ library files. No artifact → document round-trips.- Conversation history (when the agent lands in 0.2) lives in
sessions/<id>.jsonl, never indesign.json. - Permissive mode: electrical/CSP violations surface in
warnings[], do not block generation. (Strict mode is a later toggle.) - Secrets never go in
design.json. Reference fleet-for-esphome'ssecrets.yamlvia!secret name.
Library files
library/components/<id>.yamlcarries electrical metadata that ESPHome doesn't (pins, passives, current draw, pull-up requirements) plus a Jinja2 ESPHome YAML template.library/boards/<id>.yamlcarries board pinout, rails, and the PlatformIO board key.
Tests
- Generator output is pinned to goldens in
tests/golden/. - When a golden changes intentionally, regenerate via the CLI and commit the new file in the same diff as the code change.
TODOs
Use # TODO(0.x): to mark deferred work tied to a phase from START.md.
Plain # TODO: is fine for unscoped notes.
What not to do
- No new top-level documentation files unless explicitly asked.
- No splitting
wirestudio/into more packages until 0.2 needs them. - No vendoring upstream ESPHome source. Schema-derived data only.
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 · 49 lines · 511 tokens per session scan A 1a7ac4d3c02a
WireStudio CLAUDE.md is an instructions file published in the GitHub repository moellere/WireStudio (26 stars, last pushed 4d ago), licensed MIT. It adds 511 tokens to every session, about $0.0026 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
aurora-smart-home AGENTS.md
AGENTS.md instructions for tonylofgren/aurora-smart-home, covering agents.md, how to use this repo from codex, what does not carry over from claude code and repo-wide conventions.
Home-Automation CLAUDE.md
Claude Code instructions for parautenbach/Home-Automation, covering claude.md, what this is, managing home assistant, esphome and configuration architecture.
xiaozhi-esp32 AGENTS.md
AGENTS.md instructions for 78/xiaozhi-esp32, covering agents.md, project, architecture, required rules and boards and configuration.
mdb-esp32-cashless AGENTS.md
Instructions for nodestark/mdb-esp32-cashless, covering vmflow — agent context, 1. mqtt rpc — real-time device control, 2. supabase rest — data & credits, 3. agent playbooks and notes.
p3a CLAUDE.md
Claude Code instructions for fabkury/p3a, covering claude.md, project overview, build management, build commands and set pythonutf8 to avoid unicode encoding errors on windows.
ROS AGENTS.md
Instructions for lawliet206/ROS, covering agents.md, 项目是什么, 环境版本（不可随意升级/降级）, 目录结构（catkin 工作空间根 = 仓库根） and 重要 launch 与脚本（命名与参数以代码为准，改文档必须同步）.