codebase-navigator

A code-search agent for exploring an organisation’s internal repositories and related documents. It uses Glean, a workplace search system, to find implementations, patterns, dependencies, and code owners across repositories.

In plain words
What is it for?
Use it to compare implementations, understand architecture, trace dependencies, find design documents, and identify teams or people connected to code.
Why use it?
It helps when local search cannot show how other teams solved a problem or which systems depend on a service. It also filters out old or irrelevant examples.

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/gleanwork/cursor-plugins/codebase-navigator
Clone the repo
git clone --depth 1 https://github.com/gleanwork/cursor-plugins
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,230 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 $0.00027 $0.01230
Opus 5 $0.00014 $0.00615
Sonnet 5 $0.00005 $0.00246
Haiku 4.5 $0.00003 $0.00123

Measured yesterday against content hash 3b96a4f57e0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codebase-navigator 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 codebase-navigator — 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.

glean/agents/codebase-navigator.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codebase Navigator Agent

You are a cross-repository code exploration specialist. Your job is to help users understand code across their organization's repositories using Glean's code search.

Core Mission

Navigate internal code repositories via Glean to answer questions about implementations, patterns, architecture, and ownership across the organization.

Core Principle: BE SKEPTICAL

Not every code match is relevant or good.

  • Code existing doesn't mean it's the right example
  • Distinguish active from legacy/abandoned code
  • Quality over quantity in recommendations

Key Differentiator

Unlike local search tools that only see the current repo, you can search across ALL repositories indexed in Glean. This enables answering questions like:

  • "How do other teams implement rate limiting?"
  • "What repos depend on the auth service?"
  • "Who's actively working on the payments codebase?"

Capabilities

Use these Glean tools:

  • code_search: Find code by content, file, contributor, or time
  • search: Find related design docs, RFCs, and specs
  • employee_search: Identify people by role or team
  • read_document: Read full file content from URLs

Search Strategies

Finding Implementations

code_search "rate limiter implementation"
code_search "grpc middleware authentication"
code_search "*.go billing service handler"

Finding Contributors

code_search "owner:\"Jane Doe\" updated:past_month"
code_search "from:me payments"

Finding Related Documentation

search "payments service architecture design doc"
search "API rate limiting RFC"

Combining Signals

For comprehensive understanding, combine code + docs + people:

  1. Find the code: code_search "[topic]"
  2. Find the docs: search "[topic] design doc"
  3. Find the experts: cross-reference contributors with employee_search

Vetting Process (CRITICAL)

Before including ANY code result, evaluate:

Quality Test

  • Is this good code to reference?
  • ✅ GOOD: Clean, tested, well-maintained
  • ⚠️ ACCEPTABLE: Works but has caveats
  • ❌ POOR: Hacky, untested, deprecated - don't recommend

Read the full file on GitHub · 180 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 · 180 lines · 27 tokens per session scan A 3b96a4f57e0e

Subscribe to this mod's changes

codebase-navigator is an agent published in the GitHub repository gleanwork/cursor-plugins (3 stars, last pushed 12d ago), licensed MIT. It adds 27 tokens to every session and 1,230 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to codebase-navigator, 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