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.
git clone --depth 1 https://github.com/braintrustdata/braintrust-claude-pluginWrote 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/plugins/braintrustdata/braintrust-claude-plugin/trace-claude-code)<a href="https://agentmods.dev/plugins/braintrustdata/braintrust-claude-plugin/trace-claude-code"><img src="https://agentmods.dev/badge/plugins/braintrustdata/braintrust-claude-plugin/trace-claude-code/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.
<a href="https://agentmods.dev/plugins/braintrustdata/braintrust-claude-plugin/trace-claude-code"><img src="https://agentmods.dev/badge/plugins/braintrustdata/braintrust-claude-plugin/trace-claude-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
trace-claude-code 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 today.
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.
What it actually says
{
"name": "trace-claude-code",
"description": "Automatically trace Claude Code conversations to Braintrust for observability. Captures sessions, conversation turns, and tool calls as hierarchical traces.",
"version": "3.0.5",
"author": {
"name": "Braintrust"
}
}
What it installs
The manifest is a name and a version. 13 hooks travel with it, and installing the plugin installs all of them. Each is measured on its own page, and each can be installed alone.
- Hook PostToolUse A not measured
- Hook PostToolUseFailure A not measured
- Hook PreToolUse A not measured
- Hook StopFailure A not measured
- Hook SubagentStart A not measured
- Hook PostCompact A not measured
- Hook Stop A not measured
- Hook SubagentStop A not measured
- Hook UserPromptExpansion A not measured
- Hook PermissionDenied A not measured
- Hook SessionEnd A not measured
- Hook SessionStart A not measured
- Hook UserPromptSubmit A not measured
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.
- today Changed 267dcb2e5df2
- 2d ago Changed 4822da2bee12
- 22d ago Changed 9f94960aaaa5
- 27d ago Changed bf82e2d724e2
- 1mo ago Changed dbcaa8d0aa27
- 1mo ago Changed 4cab26294397
- 1mo ago First seen · 9 lines scan A d351b460e052
trace-claude-code is a plugin published in the GitHub repository braintrustdata/braintrust-claude-plugin (21 stars, last pushed today), 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 2026-08-30.
Other plugins, from other repositories
braintrust
Connect Cursor to Braintrust MCP and trace agent sessions.
langfuse
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
ai-evals
Skills for evaluating an AI product: write the eval rubric, build test inputs, turn trace notes into codes, write judges and check them against your labels. You annotate traces and label for calibration. The skills do the rest.
rawtrace-mcp
Passive Chromium CDP capture: baselines, incremental changes, and queryable browser history.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.