universal-audit-log

universal-audit-log is a plugin for Claude Code from davila7/claude-code-templates. Its token cost is not measured, scanned A, original, MIT.

An event log that records tool calls, prompts, turns, and activity from other add-ons as JSON Lines, a format with one JSON record per line. It includes timing, outcomes, and denied actions, then writes the records to a file.

In plain words
What is it for?
It is for reviewing agent activity and add-on behaviour after or during work. You can choose the log file and skip selected event types.
Why use it?
It provides a history for examining what the agent and add-ons did. Recording denied actions and durations can help trace failures or unexpected behaviour.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

Good fit It is for reviewing agent activity and add-on behaviour after or during work. You can choose the log file and skip selected event types.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add davila7/claude-code-templates
/plugin install universal-audit-log
About the project

Claude Code Templates is a command-line tool and catalogue for configuring Anthropic’s Claude Code with agents, commands, settings, hooks, integrations, skills, and project templates. Developers use it to browse and install reusable components for their coding workflows. The catalogue includes many of these Claude Code components.

davila7/claude-code-templates · 33,152 stars · on GitHub · aitmpl.com

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.

Clone the repo
git clone --depth 1 https://github.com/davila7/claude-code-templates

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 universal-audit-log

README.md
[![agentmods](https://agentmods.dev/badge/plugins/davila7/claude-code-templates/universal-audit-log/github.svg)](https://agentmods.dev/plugins/davila7/claude-code-templates/universal-audit-log)
Your own site
<a href="https://agentmods.dev/plugins/davila7/claude-code-templates/universal-audit-log"><img src="https://agentmods.dev/badge/plugins/davila7/claude-code-templates/universal-audit-log/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 universal-audit-log

Your own site · 80×15
<a href="https://agentmods.dev/plugins/davila7/claude-code-templates/universal-audit-log"><img src="https://agentmods.dev/badge/plugins/davila7/claude-code-templates/universal-audit-log.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 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.
Security

Grade A, and why

universal-audit-log 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 1mo 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.

cli-tool/components/mods/observability/universal-audit-log/.claude-plugin/plugin.json · 43 lines

What it actually says

{
  "name": "universal-audit-log",
  "version": "0.2.0",
  "description": "One hook on * that records every event on $ (tool calls, prompts, turns, other plugins' fs/http/process calls) as JSON lines with origin plugin and tier, duration and outcome, including denials. Buffered and flushed to a JSONL file through $.fs at the end of every turn.",
  "author": {
    "name": "claude-code-templates",
    "url": "https://www.aitmpl.com"
  },
  "repository": "https://github.com/davila7/claude-code-templates",
  "license": "MIT",
  "keywords": [
    "mod",
    "function-hooks",
    "observability"
  ],
  "userConfig": {
    "path": {
      "type": "string",
      "title": "Log file",
      "description": "JSONL file the audit lines are written to, relative to the working directory",
      "default": ".claude/logs/mods-audit.jsonl"
    },
    "skipEvents": {
      "type": "string",
      "title": "Skipped events",
      "description": "Comma-separated events not to record (default: render and log chatter)",
      "default": ""
    },
    "flushEvery": {
      "type": "number",
      "title": "Flush every",
      "description": "Write the buffered lines after this many events",
      "default": 50
    },
    "maxBytes": {
      "type": "number",
      "title": "Max file size",
      "description": "Keep the file under this many bytes, dropping the oldest lines",
      "default": 2097152
    }
  }
}
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. 1mo ago First seen · 43 lines scan A cde1c2f13687

Subscribe to this mod's changes

universal-audit-log is a plugin published in the GitHub repository davila7/claude-code-templates (33,152 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-17.

Related

universal-audit-log compared with plugins from other repositories

universal-audit-log next to 6 plugins from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
universal-audit-logdavila7/claude-code-templatesPlugin33kyesterdayMITA—Claude Code
databasesandisab/swe-marketplacePlugin21yesterdayMITA—Claude Code
dataandisab/swe-marketplacePlugin21yesterdayMITA—Claude Code
frontendandisab/swe-marketplacePlugin21yesterdayMITA—Claude Code
product-managementandisab/swe-marketplacePlugin21yesterdayMITA—Claude Code
commander-hub marketplaceKevinZai/commanderPlugin6yesterdayMITA—Claude Code
commanderKevinZai/commanderPlugin6yesterdayMITA—Claude Code