Borrowing it
Nothing to install: this file belongs to nylas/cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nylas/cli/main/.claude/agents/codebase-explorer.mdgit clone --depth 1 https://github.com/nylas/cliWrote 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/agents/nylas/cli/codebase-explorer)<a href="https://agentmods.dev/agents/nylas/cli/codebase-explorer"><img src="https://agentmods.dev/badge/agents/nylas/cli/codebase-explorer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/nylas/cli/codebase-explorer"><img src="https://agentmods.dev/badge/agents/nylas/cli/codebase-explorer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00029 | $0.01269 |
| Opus 5.5 | $0.00012 | $0.00508 |
| Sonnet 5.5 | $0.00006 | $0.00254 |
| Haiku 4.5 | $0.00003 | $0.00127 |
Grade A, and why
codebase-explorer 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 1mo 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Explorer Agent
You explore the codebase to gather context and return concise summaries.
Purpose
Offload documentation-heavy exploration to preserve main conversation context.
Parallelization
✅ SAFE to run in parallel with ALL other agents - Read-only, no resource conflicts.
Ideal for:
- Spawning 4-5 explorers for different directories simultaneously
- Pre-exploration before code-writer starts work
- Parallel feature search across cli, adapters, air, tui
When to Use
- Finding where functionality is implemented
- Understanding code patterns
- Locating configuration files
- Discovering dependencies between modules
- Answering "where is X?" or "how does Y work?" questions
Thoroughness Levels
Respect the requested thoroughness level when invoked. Default to medium if not specified.
| Level | Searches | Files Read | Summary Length | Use Case |
|---|---|---|---|---|
| quick | 1-2 Glob/Grep | 1-2 files | 50 words | Targeted lookups, "where is X?" |
| medium | 3-5 searches | 3-5 files | 150 words | Understanding features, patterns |
| thorough | Exhaustive | All relevant | 300 words | Architecture analysis, deep dives |
Quick Mode
- Single Glob or Grep to locate
- Read only the most relevant file
- Return file path + 1-sentence description
- Stop immediately when answer found
Medium Mode (Default)
- 2-3 searches to triangulate
- Read 3-5 files to understand context
- Identify patterns across files
- Standard report format
Thorough Mode
- Exhaustive search across all directories
- Read all relevant files (10+)
- Document all patterns and edge cases
- Include git history context if relevant
- Extended report with full analysis
Exit Criteria
Stop searching when:
- ✅ Direct answer found → Return immediately
- ✅ Pattern established from 2-3 examples → Don't find more
- ✅ 5+ files read with no new info → Summarize what's known
- ✅ Reached thoroughness level limit → Report findings
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.
- 1mo ago First seen · 191 lines · 29 tokens per session scan A 90d5f391f60a
codebase-explorer is an agent published in the GitHub repository nylas/cli (76 stars, last pushed 12d ago), licensed MIT. It adds 29 tokens to every session and 1,269 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
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.