Borrowing it
Nothing to install: this file belongs to archolet/claude-gemini-bridge. 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/archolet/claude-gemini-bridge/main/CLAUDE.mdgit clone --depth 1 https://github.com/archolet/claude-gemini-bridgeWrote 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/archolet/claude-gemini-bridge/claude-md)<a href="https://agentmods.dev/instructions/archolet/claude-gemini-bridge/claude-md"><img src="https://agentmods.dev/badge/instructions/archolet/claude-gemini-bridge/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/archolet/claude-gemini-bridge/claude-md"><img src="https://agentmods.dev/badge/instructions/archolet/claude-gemini-bridge/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 | $0.02021 | $0.02021 |
| Opus 5.5 | $0.00808 | $0.00808 |
| Sonnet 5.5 | $0.00404 | $0.00404 |
| Haiku 4.5 | $0.00202 | $0.00202 |
Grade A, and why
claude-gemini-bridge 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Gemini Bridge
Quick Start
# Install dependencies
uv sync
# Run MCP server
uv run gemini-mcp
# Run tests (excludes API-dependent tests)
uv run pytest --ignore=tests/test_phase4_ux.py
# Run specific test file
uv run pytest tests/test_phase1_gaps.py -v
Environment
# Required
export GOOGLE_CLOUD_PROJECT="your-project-id"
gcloud auth application-default login
# Optional
export GOOGLE_CLOUD_LOCATION="global"
export GEMINI_DRAFT_DIR="./temp_designs"
export GEMINI_DEV_MODE="1" # Enable hot-reload for prompt templates
Gemini 3 API Configuration
Critical Settings
- Temperature: MUST be
1.0(Gemini 3's reasoning engine is optimized for this; lowering may cause looping) - thinking_level: Controls reasoning depth
high: Complex tasks requiring deep analysislow: Latency-sensitive generation tasksminimal: Flash model only (not used in this project)
Thought Signatures
Required for multi-turn Gemini 3 conversations. Managed in AgentContext:
context.add_thought_signature(signature) # Store signature from response
context.get_latest_signatures(count=3) # Get recent signatures
context.get_signatures_for_request() # Format for next API call
Architecture
Entry Point
src/gemini_mcp/server.py- Main MCP server with all design tools
Design Tools (MCP)
| Tool | Purpose |
|---|---|
design_frontend |
Component design (button, card, navbar, etc.) |
design_page |
Full page layouts (landing, dashboard, auth) |
design_section |
Single section with style consistency |
refine_frontend |
Iterate on existing designs |
replace_section_in_page |
Surgical section replacement |
design_from_reference |
Design based on reference images |
generate_image |
Image asset generation |
validate_theme_contrast |
WCAG accessibility validation |
Multi-Agent System (Trifecta Engine)
Located in src/gemini_mcp/agents/:
| Agent | File | Role | thinking_level |
|---|---|---|---|
| Architect | architect.py |
HTML structure + Tailwind classes | high |
| Alchemist | alchemist.py |
Premium CSS effects | low |
| Physicist | physicist.py |
Vanilla JS interactions | low |
| Strategist | strategist.py |
Planning & Design DNA extraction | high |
| QualityGuard | quality_guard.py |
QA validation | low |
| Critic | critic.py |
Art direction & scoring | high |
| Visionary | visionary.py |
Vision API image analysis | high |
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 · 211 lines · 2,021 tokens per session scan A a291e962705d
claude-gemini-bridge CLAUDE.md is an instructions file published in the GitHub repository archolet/claude-gemini-bridge (0 stars, last pushed 10mo ago), licensed MIT. It adds 2,021 tokens to every session, about $0.0081 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.
claude-gemini-bridge CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| claude-gemini-bridge CLAUDE.mdarcholet/claude-gemini-bridge | Instructions file | 0 | 10mo ago | MIT | A | 2,021 | 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 |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 283k | today | MIT | A | 4,342 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |