navi: Instructions file for Claude Code

CLAUDE.md

navi CLAUDE.md is an instructions file for Claude Code from Affirm/navi. It costs 506 tokens per session, scanned D, original, BSD-3-Clause.

Instructions for Navi, a floating macOS app that monitors Claude Code sessions. It shows completed sessions and permission requests and lets users approve or deny them from one window.

In plain words
What is it for?
Setting up Navi by downloading and verifying its app release, launching it, and explaining how its plugin hooks start it during future events.
Why use it?
It reduces the need to switch between terminal windows to watch sessions or respond to permission prompts.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; names the AskUserQuestion tool; mentions Claude Code.

This is Affirm/navi's own configuration. It tells Claude Code how to work on navi 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 navi configures →

View source ↗ Affirm/navi
Reuse

Borrowing it

Nothing to install: this file belongs to Affirm/navi. 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/Affirm/navi/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Affirm/navi

Made for: Claude Code.

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 navi CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/affirm/navi/claude-md/github.svg)](https://agentmods.dev/instructions/affirm/navi/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/affirm/navi/claude-md"><img src="https://agentmods.dev/badge/instructions/affirm/navi/claude-md/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.

agentmods 80×15 button for navi CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/affirm/navi/claude-md"><img src="https://agentmods.dev/badge/instructions/affirm/navi/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 506 This file is loaded in full into every session.
When invoked 506 The same file — it is already loaded in full.
Security scan D 2 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 $0.00506 $0.00506
Opus 5.5 $0.00202 $0.00202
Sonnet 5.5 $0.00101 $0.00101
Haiku 4.5 $0.00051 $0.00051

Measured 2mo ago against content hash 8c86b5b82b57, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

navi CLAUDE.md scanned grade D with 2 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 2mo 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

**If the user wants manual-launch only**, also add `NAVI_NO_AUTO_LAUNCH` to the `env` section of `~/.claude/settings.json`:

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf /tmp/navi
CLAUDE.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Navi is a floating macOS window that monitors all your Claude Code sessions. It shows which sessions have finished, which need permission approvals, and lets you approve/deny permissions without switching terminals.

Navi is a Claude Code plugin. Hooks are defined in hooks/hooks.json and registered automatically when the plugin is installed.

This file contains instructions for Claude Code agents. For human contributor guidance (dev setup, architecture, feature flag system, how to add features), see CONTRIBUTING.md.

Setup Instructions

When the user asks to "set up Navi", "install Navi", or similar:

Before running any commands, tell the user what you're about to do (download and verify the published Navi.app release, then launch it — hooks are handled by the plugin system) and use the AskUserQuestion tool with Yes/No options to confirm before proceeding.

  1. Install the app (downloads and verifies the release artifact for the version in plugin.json):

    bash build.sh
    
  2. Launch the app:

    open Navi.app
    
  3. Confirm to the user that Navi is installed. It will auto-launch on future hook events even if closed.

If the user wants manual-launch only, also add NAVI_NO_AUTO_LAUNCH to the env section of ~/.claude/settings.json:

{
  "env": {
    "NAVI_NO_AUTO_LAUNCH": "1"
  }
}

With this set, events are still written to /tmp/navi/events/ and will be picked up when the user manually runs open Navi.app.

Removal Instructions

When the user asks to "remove Navi", "uninstall Navi", or similar:

Before running any commands, tell the user what you're about to do (kill the running app and clean up temp files) and use the AskUserQuestion tool with Yes/No options to confirm before proceeding.

  1. Kill the running app:

    pkill -x Navi 2>/dev/null
    
  2. Clean up temp files:

    rm -rf /tmp/navi
    

Read the full file on GitHub · 54 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. 2mo ago First seen · 54 lines · 506 tokens per session scan D 8c86b5b82b57

Subscribe to this mod's changes

navi CLAUDE.md is an instructions file published in the GitHub repository Affirm/navi (10 stars, last pushed 4mo ago), licensed BSD-3-Clause. It adds 506 tokens to every session, about $0.0020 per session on Opus 5.5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

navi CLAUDE.md compared with instructions from other repositories

navi CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
navi CLAUDE.mdAffirm/naviInstructions file104mo agoBSD-3-ClauseD506Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode