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/aicayzer/bigquery-mcp/claude-mdgit clone --depth 1 https://github.com/aicayzer/bigquery-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/aicayzer/bigquery-mcp/claude-md)<a href="https://agentmods.dev/instructions/aicayzer/bigquery-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/aicayzer/bigquery-mcp/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 | $0.00870 | $0.00870 |
| Opus 5 | $0.00435 | $0.00435 |
| Sonnet 5 | $0.00174 | $0.00174 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
bigquery-mcp 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 5d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Development Guidelines
This document provides guidelines for Claude when working on the BigQuery MCP project.
Task Management
Working with TASKS.md
- Completing Tasks: When you complete a task, mark it as done by changing
[ ]to[x] - Version Batches: Once all tasks for a version are complete:
- Remove completed tasks from TASKS.md
- Update CHANGELOG.md with the version changes
- Ask about incrementing the version number
Version Management
- Pre-1.0 versions use 0.x.y format
- Minor version (0.x.0) for new features/significant changes
- Patch version (0.x.y) for bug fixes and minor improvements
- When in doubt, ask whether changes warrant a new version
Code Style
Comments
- Use inline comments sparingly, only where logic is non-obvious
- Keep comments concise and to the point
- No decorative comment blocks or ASCII art
- Docstrings for all public functions/classes
Code Organization
- Functions should do one thing well
- Keep files focused and under 300 lines where possible
- Use descriptive variable names, but concise where appropriate
- Follow PEP 8 style guidelines
Git Commits
Commit Messages
- Single line, imperative mood: "Add list_projects tool"
- No emoji or decorative elements
- Be specific but concise
- Examples:
- "Add BigQuery client initialization"
- "Fix SQL validation for nested queries"
- "Update dependencies to latest versions"
Commit Frequency
- Logical, atomic commits
- One feature/fix per commit where possible
- Commit after completing each meaningful unit of work
Development Workflow
-
Before Making Changes:
- Review current TASKS.md
- Ensure understanding of the specific task
- Check for any blocking dependencies
-
While Developing:
- Write tests alongside implementation
- Run tests frequently
- Keep security in mind (no credentials in code)
-
After Changes:
- Update TASKS.md
- Make appropriate git commit(s)
- Update documentation if needed
- Note any new tasks discovered
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.
- 5d ago First seen · 141 lines · 870 tokens per session scan A 2a2f369d2de2
bigquery-mcp CLAUDE.md is an instructions file published in the GitHub repository aicayzer/bigquery-mcp (2 stars, last pushed 1y ago), licensed MIT. It adds 870 tokens to every session, about $0.0043 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
bigquery-mcp CLAUDE.md
Instructions for pvoo/bigquery-mcp, covering claude.md, project overview, development commands, setup (recommended approach) and or manual setup.
skills AGENTS.md
AGENTS.md instructions for qdrant/skills, covering qdrant skills, project overview, project structure, navigating skills locally and conventions.
agent-skills GEMINI.md
Gemini CLI instructions for mongodb/agent-skills, covering mongodb gemini extension and configuration.
llm-ide-rules python-app.instructions.md
Instructions for iloveitaly/llm-ide-rules, covering python app, factories and database & orm.
amem copilot-instructions.md
Copilot instructions for amanasmuei/amem, covering copilot instructions for amem, build, test, lint, architecture, module dependency chain and data flow.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.