savant-chat

savant-chat is a command for Claude Code from rlaope/claude-code-savant. It costs 16 tokens per session (303 once invoked), scanned A, original, MIT.

A command that launches Savant Chat, a web messenger for discussing a project with AI personas. It builds and starts the web server with the user's current project as context, then opens the local interface in a browser.

In plain words
What is it for?
Use it to build and launch the local chat interface, connect it to the current project, and open it at the configured local address.
Why use it?
It provides a browser-based way to chat about the current project instead of using only command-line interactions. Passing the project directory gives the chat the intended project context.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions Claude Code.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is cd <plugin_dir>/web && PROJECT_DIR=<user_cwd> node dist/server.js &.

Part of the claude-code-savant plugin — 29 commands, 1 MCP server shipped together

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/rlaope/claude-code-savant
agentmods
npx agentmods add commands/rlaope/claude-code-savant/savant-chat

Made for: Claude Code.

Or install claude-code-savant, the plugin that ships this one along with the rest of its 29 commands, 1 MCP server.

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 savant-chat

README.md
[![agentmods](https://agentmods.dev/badge/commands/rlaope/claude-code-savant/savant-chat.svg)](https://agentmods.dev/commands/rlaope/claude-code-savant/savant-chat)
Your own site
<a href="https://agentmods.dev/commands/rlaope/claude-code-savant/savant-chat"><img src="https://agentmods.dev/badge/commands/rlaope/claude-code-savant/savant-chat.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 303 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00016 $0.00303
Opus 5 $0.00008 $0.00151
Sonnet 5 $0.00003 $0.00061
Haiku 4.5 $0.00002 $0.00030

Measured 5d ago against content hash 9f32ff45a4c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

savant-chat 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 5d 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.

commands/savant-chat.md · 39 lines

What it actually says

Savant Chat Launcher

Launch the Savant Chat web interface directly from Claude Code.

Instructions

You MUST execute these steps in order:

  1. Find the claude-code-savant plugin directory. Check these locations:

    • ~/.claude/plugins/claude-code-savant/
    • The directory where this command file lives (go up one level from commands/)
    • Search for claude-code-savant in common plugin paths
  2. Build the web server (if not already built):

cd <plugin_dir>/web && npx tsc 2>/dev/null
  1. Start the server with the USER'S CURRENT PROJECT as context (not the plugin directory) and auto-open browser:
cd <plugin_dir>/web && PROJECT_DIR=<user_cwd> node dist/server.js &
  1. Wait 2 seconds for the server to start, then auto-open the browser:
sleep 2 && open http://localhost:3456
  1. If the build fails because dependencies aren't installed, run:
cd <plugin_dir> && npm install && cd web && npx tsc

IMPORTANT: PROJECT_DIR must be set to the user's current working directory, NOT the plugin directory. This is what gives the personas context about the user's project.

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. 5d ago First seen · 39 lines · 16 tokens per session scan A 9f32ff45a4c2

Subscribe to this mod's changes

savant-chat is a command published in the GitHub repository rlaope/claude-code-savant (2 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 303 once invoked, about $0.0001 per session on Opus 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 2026-08-31.