agent-library: Command for Gemini CLI

.gemini/commands/frontend.toml

frontend is a command for Gemini CLI from bl1nk-bot/agent-library. It costs 0 tokens per session (638 once invoked), scanned A, original, CC0-1.0.

A server-context command that loads Rust files from the Bl1nk Agents Manager server and selected core modules for the coding agent to inspect.

In plain words
What is it for?
Working on server behavior, agents, routing, configuration, rate limits, and related core code.
Why use it?
It puts the server's implementation and key shared components together so related questions can be answered with the needed context.

Command for Gemini CLI

Written for Gemini CLI: installed under .gemini/.

This is bl1nk-bot/agent-library's own configuration. It tells Gemini CLI how to work on agent-library itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-library configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bl1nk-bot/agent-library. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bl1nk-bot/agent-library/main/.gemini/commands/frontend.toml
Clone the repo
git clone --depth 1 https://github.com/bl1nk-bot/agent-library

Made for: Gemini CLI.

Wrote 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.

agentmods badge for frontend

README.md
[![agentmods](https://agentmods.dev/badge/commands/bl1nk-bot/agent-library/frontend.svg)](https://agentmods.dev/commands/bl1nk-bot/agent-library/frontend)
Your own site
<a href="https://agentmods.dev/commands/bl1nk-bot/agent-library/frontend"><img src="https://agentmods.dev/badge/commands/bl1nk-bot/agent-library/frontend.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 638 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00638
Opus 5 $0.00000 $0.00319
Sonnet 5 $0.00000 $0.00128
Haiku 4.5 $0.00000 $0.00064

Measured 2d ago against content hash 2426676b1c02, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

frontend 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 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.

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.

.gemini/commands/frontend.toml · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

description="Injects context of all relevant server files for the Bl1nk Agents Manager" prompt = """ The source code contains the content of absolutely every source code file in crates/server and key files from crates/core. You should very rarely need to read any other files from crates/server to resolve prompts.

!{find crates/server -path crates/server/target -prune -o -type f \( -name ".rs" \) ! -name ".test.rs" ! -name "Cargo.lock" -exec echo "--- {} ---" \; -exec cat {} \; && echo "--- crates/core/src/lib.rs ---" && cat crates/core/src/lib.rs && echo "--- crates/core/src/config.rs ---" && cat crates/core/src/config.rs && echo "--- crates/core/src/mcp/mod.rs ---" && cat crates/core/src/mcp/mod.rs && echo "--- crates/core/src/agents/mod.rs ---" && cat crates/core/src/agents/mod.rs && echo "--- crates/core/src/agents/router.rs ---" && cat crates/core/src/agents/router.rs && echo "--- crates/core/src/rate_limit.rs ---" && cat crates/core/src/rate_limit.rs}

Pay extremely close attention to these files. They define the project's core architecture, component patterns, and testing standards.

In addition to the code context, you MUST strictly adhere to the following backend-specific development guidelines while adding code to crates/server.

Testing Standards

  • Async Testing: ALWAYS use tokio::test attribute for async tests instead of blocking code.
  • Integration Tests: Use integration tests to verify HTTP endpoints and Rocket routes.
  • Unit Tests: Use unit tests to verify individual functions and modules.
  • Mocking:
    • Reuse existing mock patterns where possible.
    • Parameterized Tests: Use parameterized tests to reduce duplication and ensure comprehensive coverage.

Backend Architecture

  • HTTP Handling: You MUST use Rocket framework for HTTP endpoints, following the existing patterns in crates/server/src/main.rs.
  • State Management:
    • NEVER trigger blocking operations from async contexts. Use proper async/await patterns.
    • Use Arc<Mutex<T>> or tokio::sync primitives for shared state.
  • Performance:
    • Avoid blocking operations in async contexts.
    • Use proper error handling with Result types.

Read the full file on GitHub · 43 lines

Changes

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.

  1. 2d ago First seen · 43 lines · 0 tokens per session scan A 2426676b1c02

Subscribe to this mod's changes

frontend is a command published in the GitHub repository bl1nk-bot/agent-library (2 stars, last pushed 2d ago), licensed CC0-1.0. It costs nothing until one of its globs matches a file; then it loads 638 tokens. 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 2026-09-04.