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.
npx agentmods add instructions/affirm/navi/claude-mdgit clone --depth 1 https://github.com/Affirm/naviWrote 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/instructions/affirm/navi/claude-md)<a href="https://agentmods.dev/instructions/affirm/navi/claude-md"><img src="https://agentmods.dev/badge/instructions/affirm/navi/claude-md.svg" alt="Measured on agentmods" 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 | $0.00506 | $0.00506 |
| Opus 5 | $0.00253 | $0.00253 |
| Sonnet 5 | $0.00101 | $0.00101 |
| Haiku 4.5 | $0.00051 | $0.00051 |
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 3d 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 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 - Claude Code Session Monitor
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.
-
Install the app (downloads and verifies the release artifact for the version in
plugin.json):bash build.sh -
Launch the app:
open Navi.app -
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.
-
Kill the running app:
pkill -x Navi 2>/dev/null -
Clean up temp files:
rm -rf /tmp/navi
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.
- 3d ago First seen · 54 lines · 506 tokens per session scan D 8c86b5b82b57
navi CLAUDE.md is an instructions file published in the GitHub repository Affirm/navi (10 stars, last pushed 2mo ago), licensed BSD-3-Clause. It adds 506 tokens to every session, about $0.0025 per session on Opus 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.
Other instructions, from other repositories
humansintheloop-dev-workflow-and-tools CLAUDE.md
Claude Code instructions for humansintheloop-dev/humansintheloop-dev-workflow-and-tools, covering project guidelines, executing bash commands, skills, code health and referencing code locations.
minimalist copilot-instructions.md
Instructions for DivyeshJayswal/minimalist, covering minimalist (coding tasks), persistence, fast path, bias and output.
omnifocus-claude-extension CLAUDE.md
Instructions for geoffdavis/omnifocus-claude-extension, covering claude.md, project overview, essential commands, build & development and install dependencies.
VoxClaw AGENTS.md
AGENTS.md instructions for malpern/VoxClaw, covering voxclaw - codex project notes, what it is, architecture, build & test and integration methods.
agent-hive hive-workflow.instructions.md
Hive plan-first development workflow.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).