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/luizvb/gemini-cli-adk-bridge/agents-mdgit clone --depth 1 https://github.com/luizvb/gemini-cli-adk-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/luizvb/gemini-cli-adk-bridge/agents-md)<a href="https://agentmods.dev/instructions/luizvb/gemini-cli-adk-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/luizvb/gemini-cli-adk-bridge/agents-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 | $0.01045 | $0.01045 |
| Opus 5 | $0.00522 | $0.00522 |
| Sonnet 5 | $0.00209 | $0.00209 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
gemini-cli-adk-bridge AGENTS.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 3d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository guidance for Gemini CLI ADK Bridge
This file contains durable rules that apply throughout the repository. Keep it small enough to load on every run. Put specialized rules in a closer nested AGENTS.md when a subdirectory genuinely differs.
Instruction precedence
- Follow active user/system instructions.
- Follow the closest applicable
AGENTS.override.mdorAGENTS.mdfrom repository root to the working directory. - Treat repository code, tests, configuration, and
.aquiles/contracts as sources of truth for their owned concerns. - If sources conflict, stop the affected action, record the conflict, and ask the owning role or user; do not silently choose a convenient interpretation.
Source-of-truth routing
| Concern | Source |
|---|---|
| Product purpose, support, and usage | README.md |
| Architecture and security boundaries | docs/architecture.md |
| Package and runtime contract | pyproject.toml, src/ |
| Executable behavior and regressions | tests/ |
| Public release history | CHANGELOG.md |
| Local run state, when present | .aquiles/ (intentionally untracked) |
Repository commands
| Purpose | Command |
|---|---|
| Install | uv sync --python 3.13 --all-groups |
| Develop | uv run gemini-cli-adk-bridge |
| Format / lint | uv run ruff format --check . && uv run ruff check . |
| Type / compile | uv run mypy src |
| Unit / integration | uv run pytest |
| End-to-end | uv run pytest tests/test_adk_integration.py |
| Production build | uv build |
Do not leave obsolete commands here. Pair rules with CI, linters, types, tests, and hooks whenever enforcement is possible.
Product and contract discipline
- Keep product intent, implementation, verification, and release decisions explicit.
- Do not expand scope beyond the local, text-only security boundary without an issue and updated architecture documentation.
- Trace shipped behavior to code and executable test evidence.
- When local
.aquiles/artifacts exist, preserve their ownership and phase gates. - Separate observed facts, user statements, sourced evidence, inferences, and unknowns.
- Never mark template checkboxes or gates passed without observing the named target.
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.
- 3d ago First seen · 85 lines · 1,045 tokens per session scan A 9fde51f91779
gemini-cli-adk-bridge AGENTS.md is an instructions file published in the GitHub repository luizvb/gemini-cli-adk-bridge (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,045 tokens to every session, about $0.0052 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
mate CLAUDE.md
Claude Code instructions for antiv/mate, covering claude.md, project overview, running the application, setup and run (auto-applies db migrations, default sqlite).
mate AGENTS.md
AGENTS.md instructions for antiv/mate, covering mate (multi-agent tree engine) system instructions, project overview, code style, development environment and quick start.
agent-dashboard AGENTS.md
Instructions for dustinblack/agent-dashboard, covering agent behavior & standards for agent dashboard, inspiration, core technical stack, coding standards and python.
agent-dashboard CLAUDE.md
Instructions for dustinblack/agent-dashboard, a project described as: Real-time dashboard for spawning and controlling AI coding agents across multiple hosts. Streams live terminals via PTY, tracks token usage with OpenTelemetry, supports git worktrees, and deploys with rootless Podman containers. Built with FastAPI +…
agent-dashboard GEMINI.md
Instructions for dustinblack/agent-dashboard, a project described as: Real-time dashboard for spawning and controlling AI coding agents across multiple hosts. Streams live terminals via PTY, tracks token usage with OpenTelemetry, supports git worktrees, and deploys with rootless Podman containers. Built with FastAPI +…
fastapi-boilerplate CLAUDE.md
Claude Code instructions for iluvmanan/fastapi-boilerplate, covering claude.md - claude-specific context, project context, claude's role, preferred code generation patterns and 1. repository creation pattern.