Borrowing it
Nothing to install: this file belongs to bin2ai/powertree. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bin2ai/powertree/main/CLAUDE.mdgit clone --depth 1 https://github.com/bin2ai/powertreeWrote 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/bin2ai/powertree/claude-md)<a href="https://agentmods.dev/instructions/bin2ai/powertree/claude-md"><img src="https://agentmods.dev/badge/instructions/bin2ai/powertree/claude-md/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/instructions/bin2ai/powertree/claude-md"><img src="https://agentmods.dev/badge/instructions/bin2ai/powertree/claude-md.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 | $0.01430 | $0.01430 |
| Opus 5.5 | $0.00572 | $0.00572 |
| Sonnet 5.5 | $0.00286 | $0.00286 |
| Haiku 4.5 | $0.00143 | $0.00143 |
Grade A, and why
powertree 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 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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - PowerTree
Read this first. Project-local guidance for how to work here.
Project
- What: Local Windows Python app for electronic circuit power tree analysis - sources, converters, loads, series elements, blocks; bottom-up power calc; list + flowchart views; PDF/Excel/image/markdown exports.
- Started: 2026-08-06
- Status: v0.1 working app.
main.pylaunches the PySide6 GUI (orPowerTree.bat). 14 pytest tests intests/cover solver math + serialization. Demo file atexamples/DemoBoard.ptproj.
Architecture (read before editing)
src/powertree/model/elements.py— dataclasses (Source/Converter/Load/SeriesElement/ Block/Note), tree constraints (ONE source per tree, loads are leaves).src/powertree/model/calc.py— bottom-up solver, 3 corners (min/typ/max), damped fixed-point for series-R × power-load; margin warnings. ALL electrical math lives here.src/powertree/model/serialization.py—.ptprojversioned JSON (self-contained, notes + base64 images embedded).src/powertree/ui/layout.py— pure-Python tidy-tree layout + orthogonal edge routing (no Qt).canvas.py— QGraphicsScene flowchart + headlessrender_tree_image()used by exports.mainwindow.py— all wiring;refresh()is the auto-refresh funnel.src/powertree/export/— pdf_report, excel_export (openpyxl + COM .xlsm), image, notes MD/HTML/PDF, md_render (shared markdown→flowables/HTML).- Run tests:
.venv\Scripts\python.exe -m pytest tests -q. - Headless GUI/render testing: set
QT_QPA_PLATFORM=offscreenandQT_QPA_FONTDIR=C:\Windows\Fonts(else text renders as tofu boxes).
Folder structure
CLAUDE.md # this file - how Claude should work here
MEMORY.md # running log: status, decisions, deliverables, open threads
README.md # human-facing overview (what / why / how to run)
.obsidian/ # makes this folder an Obsidian vault (notes are .md)
.claude/ # settings.local.json (permissions) + hooks/
notes/ # Obsidian knowledge base - link with [[wikilinks]]
research/ # gathered sources, raw findings, agent dumps
artifacts/ # deliverables: reports, PDFs, exports, builds
scratch/ # throwaway / working files (safe to delete; gitignored)
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 · 90 lines · 1,430 tokens per session scan A d859beb11f47
powertree CLAUDE.md is an instructions file published in the GitHub repository bin2ai/powertree (1 stars, last pushed 3mo ago), licensed MIT. It adds 1,430 tokens to every session, about $0.0057 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 2026-08-31.
powertree CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| powertree CLAUDE.mdbin2ai/powertree | Instructions file | 1 | 3mo ago | MIT | A | 1,430 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 8,130 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |
| generative-ai-for-beginners AGENTS.mdmicrosoft/generative-ai-for-beginners | Instructions file | 124k | today | MIT | A | 2,981 | Codex, OpenCode |