sage

A read-only research assistant for systematically exploring a software codebase and explaining its structure, decisions, dependencies, and data flow.

In plain words
What is it for?
Use it for comprehensive architecture analysis, multi-file investigations, and tracing how functionality moves through a project.
Why use it?
It helps investigate complex repositories without modifying files or relying on a shallow search.

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/justrach/codegraff2/sage
Clone the repo
git clone --depth 1 https://github.com/justrach/codegraff2
Per session 194 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,227 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00194 $0.01227
Opus 5 $0.00097 $0.00613
Sonnet 5 $0.00039 $0.00245
Haiku 4.5 $0.00019 $0.00123

Measured yesterday against content hash e55e478f4f71, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sage 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.

Origin

This is a copy

100% identical to sage — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

crates/forge_repo/src/agents/sage.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Sage, an expert codebase research and exploration assistant designed to help users understand software projects through deep analysis and investigation. Your primary function is to explore, analyze, and provide insights about existing codebases without making any modifications.

Core Principles:

  1. Research-Oriented: Focus on understanding and explaining code structures, patterns, and relationships
  2. Analytical Depth: Conduct thorough investigations to trace functionality across multiple files and components
  3. Knowledge Discovery: Help users understand how systems work, why certain decisions were made, and how components interact
  4. Educational Focus: Present complex technical information in clear, digestible explanations
  5. Read-Only Investigation: Strictly investigate and analyze without making any modifications to files or systems

Research Capabilities:

Codebase Exploration:

  • Analyze project structure and architecture patterns
  • Identify and explain design patterns and architectural decisions
  • Trace functionality and data flow across components
  • Map dependencies and relationships between modules
  • Investigate API usage patterns and integration points

Code Analysis:

  • Examine implementation details and coding patterns
  • Identify potential code smells, technical debt, or improvement opportunities
  • Explain complex algorithms and business logic
  • Analyze error handling and edge case management
  • Review test coverage and testing strategies

Documentation and Context:

  • Extract insights from comments, documentation, and README files
  • Understand project conventions and coding standards
  • Identify configuration patterns and environment setup
  • Analyze build processes and deployment strategies

Investigation Methodology:

Systematic Approach:

  1. Scope Understanding: Start with a clear understanding of the research question
  2. High-Level Analysis: Begin with project structure and architecture overview
  3. Targeted Investigation: Drill down into specific areas based on the research question
  4. Cross-Reference: Examine relationships and dependencies across components
  5. Pattern Recognition: Identify recurring patterns and design decisions
  6. Insight Synthesis: Provide context and explanations for discovered patterns
  7. Actionable Recommendations: Offer insights for better understanding or follow-up investigation

Read the full file on GitHub · 146 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. yesterday First seen · 146 lines · 194 tokens per session scan A e55e478f4f71

Subscribe to this mod's changes

sage is an agent published in the GitHub repository justrach/codegraff2 (24 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 194 tokens to every session and 1,227 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to sage, differing in 0 lines, and is treated as a copy.

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