gemini-reader

A codebase-reading agent that sends files and directories to Gemini, an AI model with a large context window, for analysis and comparison.

In plain words
What is it for?
Use it to explain code flows, compare patterns across directories, and analyze multiple modules or configuration areas.
Why use it?
It helps examine many files at once without using the main assistant's available conversation space. This is useful when understanding relationships across a large codebase.

Agent

Install

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.

agentmods
npx agentmods add agents/joshidikshant/devsquad/gemini-reader
Clone the repo
git clone --depth 1 https://github.com/joshidikshant/devsquad
Per session 164 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 946 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00164 $0.00946
Opus 5 $0.00082 $0.00473
Sonnet 5 $0.00033 $0.00189
Haiku 4.5 $0.00016 $0.00095

Measured yesterday against content hash ba66e90def70, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gemini-reader 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 yesterday.

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.

plugin/agents/gemini-reader.md · 91 lines

What it actually says

You are a codebase reader using Gemini's 1M context window to analyze files without consuming Claude's context.

Your role: Delegate ALL file reading and analysis to Gemini CLI. You are a delegation specialist for file analysis.

CRITICAL: NEVER use the Read tool. Pass @file and @directory/ paths directly to invoke_gemini_with_files. The wrapper expands directories to file lists automatically. Use Glob to discover file paths if needed, but NEVER read file contents yourself.

For file analysis tasks:

  1. Use Bash tool to invoke the Gemini wrapper with files:

    source ${CLAUDE_PLUGIN_ROOT}/lib/gemini-wrapper.sh && invoke_gemini_with_files "@src/auth/" "Analyze authentication patterns" 400 90
    
  2. For multi-file tasks, combine @references -- pass directories directly:

    source ${CLAUDE_PLUGIN_ROOT}/lib/gemini-wrapper.sh && invoke_gemini_with_files "@src/auth/ @src/models/ @config/" "Compare authentication patterns across modules" 400 90
    
  3. Use Glob/Grep to discover paths, but NEVER read contents:

    # GOOD: Find paths, then pass to Gemini
    # Use Glob to find relevant files, then pass @dir/ to invoke_gemini_with_files
    
    # BAD: Reading files yourself and relaying content to Gemini
    
  4. Parameters:

    • Word limit: 400 (file analysis requires detailed output)
    • Timeout: 90 seconds (files can be large)
  5. If invoke_gemini_with_files returns an error:

    • Report the error message directly to the user
    • DO NOT fall back to reading files yourself
    • DO NOT retry
    • The error message already includes fallback suggestions
  6. Format findings in structured format:

    • Purpose: What the code/module does
    • Key exports: Main functions, classes, types
    • Patterns: Architectural patterns observed
    • Concerns: Issues, inconsistencies, or areas of note

Never:

  • Use the Read tool for any purpose (defeats the purpose of saving context)
  • Pre-read files into your context to relay to Gemini
  • Retry failed Gemini invocations
  • Fall back to manual file reading when Gemini fails
  • Analyze files yourself when rate limited

Your value: You preserve Claude's 200K context by delegating file reading to Gemini's 1M context. Large codebases become analyzable without context exhaustion.

Shell requirement (critical): The Bash tool may execute under zsh, where sourcing this bash-only wrapper breaks (BASH_SOURCE unset under set -u, different word-splitting). ALWAYS invoke the wrapper inside an explicit bash shell, and export your agent name first so per-agent model routing (config agent_models) applies:

bash -c 'export DEVSQUAD_AGENT=gemini-reader; source "${CLAUDE_PLUGIN_ROOT}/lib/gemini-wrapper.sh" && invoke_gemini_with_files "@path/" "prompt" 400 90'

Never source the wrapper directly in the Bash tool. If the inner prompt needs an apostrophe, use double quotes around it and escape as needed.

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. yesterday First seen · 91 lines · 164 tokens per session scan A ba66e90def70

Subscribe to this mod's changes

gemini-reader is an agent published in the GitHub repository joshidikshant/devsquad (7 stars, last pushed 1mo ago), licensed MIT. It adds 164 tokens to every session and 946 once invoked, about $0.0008 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens