update-claude

update-claude is a command for coding agents from AojdevStudio/dev-utils-marketplace. It costs 13 tokens per session (793 once invoked), scanned A, original, MIT.

A command that reviews recent code changes and Git history, then updates a project's CLAUDE.md guidance file. CLAUDE.md is a document that tells Claude Code how to work in a codebase.

In plain words
What is it for?
Use it to update instructions for the whole project or a selected directory after reviewing recent commits, changed files, and code structure.
Why use it?
It keeps the project's agent instructions aligned with how the code has changed, instead of relying on outdated documentation.

Command

Part of the documentation plugin — 3 commands, 2 agents, 1 hook shipped together

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/aojdevstudio/dev-utils-marketplace/update-claude
Clone the repo
git clone --depth 1 https://github.com/AojdevStudio/dev-utils-marketplace

Or install documentation, the plugin that ships this one along with the rest of its 3 commands, 2 agents, 1 hook.

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 update-claude

README.md
[![agentmods](https://agentmods.dev/badge/commands/aojdevstudio/dev-utils-marketplace/update-claude.svg)](https://agentmods.dev/commands/aojdevstudio/dev-utils-marketplace/update-claude)
Your own site
<a href="https://agentmods.dev/commands/aojdevstudio/dev-utils-marketplace/update-claude"><img src="https://agentmods.dev/badge/commands/aojdevstudio/dev-utils-marketplace/update-claude.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 793 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 $0.00013 $0.00793
Opus 5 $0.00006 $0.00396
Sonnet 5 $0.00003 $0.00159
Haiku 4.5 $0.00001 $0.00079

Measured 3d ago against content hash e60c415a1f5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update-claude 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 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.

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.

documentation/commands/update-claude.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Claude.md

Use Serena-first analysis to update CLAUDE.md based on recent code changes and git history.

Variables

TARGET_DIRECTORY: {{if flags.directory}}{{flags.directory}}{{else}}.{{endif}} CLAUDE_FILE: {{if flags.directory}}{{flags.directory}}/CLAUDE.md{{else}}CLAUDE.md{{endif}} ANALYSIS_SCOPE: {{if flags.directory}}directory-specific{{else}}project-wide{{endif}}

Workflow

1. Initial Setup

  • Check Serena onboarding: mcp__serena__check_onboarding_performed
  • If not onboarded, complete onboarding process first
  • Use mcp__serena__think_about_task_adherence to validate update scope

2. Git Analysis

  • Get current status: !git status --porcelain
  • Review recent commits: !git log --oneline -10
  • Analyze changed files: !git diff HEAD~5 --name-only | head -20
  • Check key file modifications: !git diff --name-status HEAD~10 | grep "^M" | head -10
  • Store git insights: mcp__serena__write_memory --memory_name="git_analysis"

3. Serena Codebase Analysis

  • Analyze directory structure: mcp__serena__list_dir --relative_path="TARGET_DIRECTORY" --recursive=true
  • For each modified file from git analysis:
    • Get symbol overview: mcp__serena__get_symbols_overview --relative_path="<FILE>"
    • Find new symbols: mcp__serena__find_symbol --name_path="<NEW_SYMBOLS>"
    • Check symbol impact: mcp__serena__find_referencing_symbols --name_path="<KEY_SYMBOLS>"
  • Store symbol analysis: mcp__serena__write_memory --memory_name="symbol_changes"

4. Content Integration

  • Read existing CLAUDE.md file: @CLAUDE_FILE
  • Use mcp__serena__think_about_collected_information to validate analysis
  • Update CLAUDE.md based on @ai-docs/serena-enhanced-claude-template.md:
    • Project overview with new architecture patterns
  • Save updated CLAUDE.md to CLAUDE_FILE location

5. Validation

  • Use mcp__serena__think_about_whether_you_are_done to verify completeness
  • Store update insights: mcp__serena__write_memory --memory_name="claude_update_ANALYSIS_SCOPE"

Read the full file on GitHub · 86 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. 3d ago First seen · 86 lines · 13 tokens per session scan A e60c415a1f5d

Subscribe to this mod's changes

update-claude is a command published in the GitHub repository AojdevStudio/dev-utils-marketplace (2 stars, last pushed 6mo ago), licensed MIT. It adds 13 tokens to every session and 793 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.