Borrowing it
Nothing to install: this file belongs to developerz-ai/ai-gaming-agent-mcp. 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/developerz-ai/ai-gaming-agent-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/developerz-ai/ai-gaming-agent-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/developerz-ai/ai-gaming-agent-mcp/claude-md)<a href="https://agentmods.dev/instructions/developerz-ai/ai-gaming-agent-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/developerz-ai/ai-gaming-agent-mcp/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/developerz-ai/ai-gaming-agent-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/developerz-ai/ai-gaming-agent-mcp/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 | $0.02226 | $0.02226 |
| Opus 5.5 | $0.00890 | $0.00890 |
| Sonnet 5.5 | $0.00445 | $0.00445 |
| Haiku 4.5 | $0.00223 | $0.00223 |
Grade C, and why
ai-gaming-agent-mcp CLAUDE.md scanned grade C with 1 finding 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 2d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| `security.blocked_commands` | `["rm -rf", "format", "del /f", "mkfs"]` | Command blocklist. | How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Repository brain for AI Gaming Agent: an MCP server for remote PC automation. Package version: 0.2.0.
Non-negotiable rules
| Rule | Requirement |
|---|---|
| Gate | bin/check is the gate. Red is not a pull request; fix the cause. |
| Verify | Run the narrowest relevant check first; the harness runs the full gate after all editors finish. |
| Tests | Reproduce a bug with a failing test before fixing it. Never delete or weaken a test to get green. |
| Guards | Never silence a lint, type, test, or security guard. A machine-enforced rule wins. |
| Disclosure | Agents are bots; disclose that in usernames and every comment. Never impersonate a human. |
| Merge gates | CI, review verdict, and branch protection decide merges. Never merge around red or missing gates; never self-approve. |
| Bot etiquette | Never argue with or reply to another bot. Act on dependency-bot PRs like any other PR. |
| Checkout | One checkout and branch. Never create a worktree; the harness owns commits, pushes, and PRs. |
| File ownership | Edit only your assigned paths; report other required paths instead of touching them. |
| Credentials | Resolve secrets from the vault at point of use. Never expose them in context, logs, comments, or commits. |
| Scope | Do one task. Report unrelated defects separately; do not bundle them. |
| Change discipline | Read before editing; make the smallest correct change; keep files under 500 LOC. |
| Tool changes | Follow .claude/agents/mcp-tools.md: registry, export, workflow dispatch, tests, and docs stay aligned. |
| GUI imports | Keep PyAutoGUI/Pillow-heavy imports lazy so CI needs no display. |
| Tool results | Return dictionaries with consistent success and error keys. |
Stack
| Area | Declared stack |
|---|---|
| Language | Python >=3.12 |
| Package/build | uv, Hatchling |
| MCP | mcp>=1.0.0 |
| HTTP | FastAPI >=0.115, uvicorn[standard] >=0.32 |
| Automation | PyAutoGUI >=0.9.54, Pillow >=10, pyperclip >=1.8 |
| Configuration | Pydantic >=2, pydantic-settings >=2 |
| System | screeninfo >=0.8.1, psutil >=6 |
| VLM (optional) | Ollama >=0.4 via the vlm extra |
| Quality | Ruff >=0.8; pytest >=8 and pytest-asyncio >=0.24 via the dev extra |
| Integration extra | pytest and pytesseract >=0.3.10 |
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.
- 2d ago Changed · -213 lines · -774 tokens per session aa266810ba3d
- 2mo ago First seen · 365 lines · 3,000 tokens per session scan C 1c5a1fcc6b56
ai-gaming-agent-mcp CLAUDE.md is an instructions file published in the GitHub repository developerz-ai/ai-gaming-agent-mcp (2 stars, last pushed 2d ago), licensed MIT. It adds 2,226 tokens to every session, about $0.0089 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
ai-gaming-agent-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ai-gaming-agent-mcp CLAUDE.mddeveloperz-ai/ai-gaming-agent-mcp | Instructions file | 2 | 2d ago | MIT | C | 2,226 | 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 | yesterday | 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 |