Borrowing it
Nothing to install: this file belongs to whanyu1212/gem-dota. 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/whanyu1212/gem-dota/main/CLAUDE.mdgit clone --depth 1 https://github.com/whanyu1212/gem-dotaWrote 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/whanyu1212/gem-dota/claude-md)<a href="https://agentmods.dev/instructions/whanyu1212/gem-dota/claude-md"><img src="https://agentmods.dev/badge/instructions/whanyu1212/gem-dota/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/whanyu1212/gem-dota/claude-md"><img src="https://agentmods.dev/badge/instructions/whanyu1212/gem-dota/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 | $0.10889 | $0.10889 |
| Opus 5.5 | $0.04356 | $0.04356 |
| Sonnet 5.5 | $0.02178 | $0.02178 |
| Haiku 4.5 | $0.01089 | $0.01089 |
Grade A, and why
gem-dota 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 10d 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 — 742 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
This project is managed with uv. Prefer uv run — it uses the project's
.venv without a manual source .venv/bin/activate. (CONTRIBUTING.md has the
fuller contributor workflow; the list below is the day-to-day short version.)
# Install project + dev dependencies
uv sync --group dev
# Run default test suite (skips slow/integration/network markers via pyproject.toml)
uv run pytest
# Run all tests, including slow/integration/network markers
uv run pytest -m ""
# Run a single test file
uv run pytest tests/binary/test_reader.py
# Run a single test by name
uv run pytest tests/binary/test_reader.py::TestReadBits::test_read_8_bits
# Run with coverage
uv run pytest --cov=gem --cov-report=term-missing
# Explicit fast loop — equivalent to the default marker filter
uv run pytest -m "not slow and not integration and not network"
# Offline integration suite (requires local replay fixtures); 4 workers, one per
# shared parsed replay (tests/conftest.py groups them)
uv run pytest -m "integration and not network" -n 4 --dist loadgroup
# OpenDota parity checks the parity audit repeats; run with the audit
uv run pytest -m corpus -n 4 --dist loadgroup
# All offline tests
uv run pytest -m "not network"
# Live network smoke
uv run pytest -m network
# Broader remote draft integration sample (downloads/parses 5 pro replays)
GEM_DRAFT_INTEGRATION_FULL=1 uv run pytest tests/test_draft_integration.py -m integration
# Lint, format, type-check (run before committing)
uv run ruff check src/ tests/
uv run ruff format src/ tests/
uv run mypy src/gem/
# Regenerate protobuf modules after updating proto_definitions/
uv run python scripts/compile_protos.py
# Docs — the Astro site lives in site/ (Node 22+, see "Docs" below)
cd site && npm install && npm run dev
Architecture
Note:
STRATEGY.md(the original implementation plan referenced in older versions of this file) has been removed. The living architecture references are nowsite/src/content/docs/architecture.mdand thesite/src/content/docs/deep-dives/pages.CHANGELOG.mdis the authoritative record of what shipped in each release.
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.
- 10d ago Changed · +10 lines · +176 tokens per session 2f9eb22e80f9
- 11d ago Changed · +2 tokens per session c926b39df2bf
- 22d ago Changed · -5 tokens per session 9454fbbfeaa6
- 23d ago Changed · +8 lines · +118 tokens per session 41c55331f7a5
- 1mo ago Changed · +12 lines · +257 tokens per session 93bde4d8ff54
- 1mo ago Changed · +17 lines · +348 tokens per session 68ffc463babd
- 1mo ago Changed · +4 lines · +87 tokens per session 481b5e310517
- 1mo ago Changed · +15 lines · +299 tokens per session fc6d489a7ab8
- 1mo ago Changed · +24 lines · +476 tokens per session d292cac8e1a9
- 1mo ago First seen · 652 lines · 9,131 tokens per session scan A 8542072cbf0d
gem-dota CLAUDE.md is an instructions file published in the GitHub repository whanyu1212/gem-dota (157 stars, last pushed 7d ago), licensed MIT. It adds 10,889 tokens to every session, about $0.0436 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 2026-08-30.
gem-dota CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gem-dota CLAUDE.mdwhanyu1212/gem-dota | Instructions file | 157 | 7d ago | MIT | A | 10,889 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |