update

An update command for Claude Code Savant, installed as a local copy of a Git repository. A Git repository is a project folder that tracks changes and can download newer versions from a shared source.

In plain words
What is it for?
Use it to compare the installed Savant version with the remote project, review recent commits, and pull available updates.
Why use it?
It removes the manual work of checking the installed version, finding new changes, and updating the local copy.

Command

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 commands/rlaope/claude-code-savant/update
Clone the repo
git clone --depth 1 https://github.com/rlaope/claude-code-savant
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 552 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 $0.00011 $0.00552
Opus 5 $0.00005 $0.00276
Sonnet 5 $0.00002 $0.00110
Haiku 4.5 $0.00001 $0.00055

Measured 2d ago against content hash 3a56d256f8da, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update 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 2d 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/update.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Savant Update

$ARGUMENTS

Your Task

Check for updates and upgrade claude-code-savant to the latest version using git pull.

Step 1: Find Plugin Directory

The plugin is installed as a local git clone. Find the directory:

# The plugin directory is where this command file lives
PLUGIN_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"

Use Bash to run:

cd <plugin-directory> && git remote -v

Verify it's a git repo pointing to rlaope/claude-code-savant.

Step 2: Check Current Version

Read package.json in the plugin directory to get the current version.

Step 3: Fetch Latest and Compare

Run these commands in the plugin directory:

git fetch origin master

Then check if there are updates:

git log HEAD..origin/master --oneline

If No Updates

Also run:

git log --oneline -10

Report:

## ✅ Already up to date!

**Current Version**: [version]
No new commits on origin/master.

### 📋 Recent Activity
[list of recent 10 commits from git log]

Stop here.

If Updates Available

Show the user what's coming:

## 🔄 Update Available!

**Current Version**: [current version]
**New commits**:
[list of commits from git log]

Step 4: Pull and Rebuild

Ask the user for confirmation, then:

git pull origin master && npx tsc

Step 5: Verify

Read the updated package.json to confirm the new version.

Report:

## ✅ Updated Successfully!

**Previous Version**: [old]
**New Version**: [new]

Restart Claude Code to use the new version.

Step 6: If Web UI is Running

If the Savant Chat web UI was running, remind the user:

💡 If Savant Chat was running, restart it:
   lsof -ti:3456 | xargs kill -9 2>/dev/null; npm run chat

Error Handling

  • Not a git repo: Tell user to clone from https://github.com/rlaope/claude-code-savant
  • Merge conflicts: Run git stash && git pull origin master && git stash pop
  • Build fails: Run npx tsc again and report errors

Read the full file on GitHub · 115 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. 2d ago First seen · 115 lines · 11 tokens per session scan A 3a56d256f8da

Subscribe to this mod's changes

update is a command published in the GitHub repository rlaope/claude-code-savant (2 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 552 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.