trace-claude-code — Claude Code skill: what it does, how to install
trace-claude-code streams Claude Code interactions directly into Braintrust. Captures multi-turn conversations, tool executions, and file edits as structured spans.
MIT ★ 3,951 updated 2026-01-26
npx skills add parcadei/Continuous-Claude-v3 --skill trace-claude-code -a claude-codeWhat trace-claude-code does
This skill integrates observability directly into local coding workflows by forwarding activity to Braintrust. Each Claude Code execution forms a structured hierarchy: the root task span tracks the overall session, nested records log each turn with input and output messages, and individual tool events capture terminal commands alongside file modifications.
Under the hood, four bash routines handle tracking: session_start.sh initialises the trace, post_tool_use.sh monitors tool operations, stop_hook.sh aggregates message pairs, and session_end.sh writes the closing summary. Configuration is applied via setup.sh or through hook declarations inside .claude/settings.local.json.
Tracing relies strictly on the command-line utility jq and a valid BRAINTRUST_API_KEY. Without TRACE_TO_BRAINTRUST set to "true", outgoing trace delivery remains completely inactive.
What it helps with
- stream Claude Code execution history into Braintrust dashboards
- inspect granular tool invocations including terminal actions and file diffs
- debug failed assistant workflows using local trace logs
- structure development sessions into parent spans and individual conversational turns
Example prompts for the agent
- Run the setup script for trace-claude-code to configure my Braintrust key
- Add the trace hooks into my local
.claude/settings.local.jsonfile - Check the debug output inside
~/.claude/state/braintrust_hook.log
How to install trace-claude-code
1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill trace-claude-code -a claude-code2Manually: put the files in place
~/.claude/skills/trace-claude-code/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/trace-claude-code/
1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill trace-claude-code -a codex2Manually: put the files in place
.agents/skills/trace-claude-code/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill trace-claude-code -a cursor2Manually: put the files in place
.cursor/skills/trace-claude-code/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install parcadei/Continuous-Claude-v3 .claude/plugins/braintrust-tracing/skills/trace-claude-code2Manually: put the files in place
.github/skills/trace-claude-code/SKILL.md1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill trace-claude-code -a gemini-cli2Platform CLI
gemini skills install https://github.com/parcadei/Continuous-Claude-v3 --path .claude/plugins/braintrust-tracing/skills/trace-claude-codeManually: put the files in place
.devin/skills/trace-claude-code/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about trace-claude-code
How to install trace-claude-code in Claude Code?
Run npx skills add parcadei/Continuous-Claude-v3 --skill trace-claude-code -a claude-code in your terminal or place the file into ~/.claude/skills/trace-claude-code/SKILL.md.
What does trace-claude-code do?
It intercepts session lifecycles, assistant turns, and tool executions in Claude Code, converting them into hierarchical observability traces inside Braintrust.
What dependencies are needed for the scripts?
You need jq available in your command line and executable permissions granted on all .sh files inside the hooks directory.
Source text
SKILL.md · MIT
---
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: 1.1.0
---
# Trace Claude Code to Braintrust
Automatically send Claude Code conversations to Braintrust for tracing and observability. Get full visibility into your AI coding sessions with hierarchical traces showing sessions, turns, and every tool call.
## What you get
```
Claude Code Session (root trace)
├── Turn 1: "Add error handling"
│ ├── Read: src/app.ts
│ ├── Edit: src/app.ts
│ └── Response: "I've added try-catch..."
├── Turn 2: "Now run the tests"
│ ├── Terminal: npm test
│ └── Response: "All tests pass..."
└── Turn 3: "Great, commit this"
├── Terminal: git add .
├── Terminal: git commit -m "..."
└── Response: "Changes committed..."
```
## How it works
Four hooks capture the complete workflow:
| Hook | What it captures |
|------|------------------|
| **SessionStart** | Creates root trace when you start Claude Code |
| **PostToolUse** | Captures every tool call (file reads, edits, terminal commands) |
| **Stop** | Captures conversation turns (your message + Claude's response) |
| **SessionEnd** | Logs session summary when you exit |
## Quick setup
Run the setup script in any project directory where you want tracing:
```bash
bash /path/to/skills/trace-claude-code/setup.sh
```
The script prompts for your API key and project name, then configures all hooks automatically.
## Manual setup
### Prerequisites
- [Claude Code CLI](https://docs.anthropic.com/en/docs/claude-code) installed
- [Braintrust API key](https://www.braintrust.dev/app/settings/api-keys)
- `jq` command-line tool (`brew install jq` on macOS)
### Configuration
Create `.claude/settings.local.json` in your project directory:
```json
{
"hooks": {
"SessionStart": [
{
"hooks": [
{
"type": "command",
"command": "bash /path/to/hooks/session_start.sh"
}
]
}
],
"PostToolUse": [
{
"matcher": "*",
"hooks": [
{
"type": "command",
"command": "bash /path/to/hooks/post_tool_use.sh"
}
]
}
],
"Stop": [
{
"hooks": [
{
"type": "command",
"command": "bash /path/to/hooks/stop_hook.sh"
}
]
}
],
"SessionEnd": [
{
"hooks": [
{
"type": "command",
"command": "bash /path/to/hooks/session_end.sh"
}
]
}
]
},
"env": {
"TRACE_TO_BRAINTRUST": "true",
"BRAINTRUST_API_KEY": "sk-...",
"BRAINTRUST_CC_PROJECT": "my-project"
}
}
```
Replace `/path/to/hooks/` with the actual path to this skill's hooks directory.
### Environment variables
| Variable | Required | Description |
|----------|----------|-------------|
| `TRACE_TO_BRAINTRUST` | Yes | Set to `"true"` to enable tracing |
| `BRAINTRUST_API_KEY` | Yes | Your Braintrust API key |
| `BRAINTRUST_CC_PROJECT` | No | Project name (default: `claude-code`) |
| `BRAINTRUST_CC_DEBUG` | No | Set to `"true"` for verbose logging |
## Viewing traces
After running Claude Code with tracing enabled:
1. Go to [braintrust.dev](https://www.braintrust.dev)
2. Navigate to your project (e.g., `claude-code`)
3. Click **Logs** to see all traced sessions
Each trace shows:
- **Session root**: The overall Claude Code session
- **Turns**: Each conversation exchange (user input → assistant response)
- **Tool calls**: Individual operations (file reads, edits, terminal commands)
## Trace structure
Traces are hierarchical:
- **Session** (root span)
- `span_attributes.type`: `"task"`
- `metadata.session_id`: Unique session identifier
- `metadata.workspace`: Project directory
- **Turn** (child of session)
- `span_attributes.type`: `"llm"`
- `input`: User message
- `output`: Assistant response
- `metadata.turn_number`: Sequential turn number
- **Tool call** (child of turn or session)
- `span_attributes.type`: `"tool"`
- `input`: Tool input (file path, command, etc.)
- `output`: Tool result
- `metadata.tool_name`: Name of the tool used
## Troubleshooting
### No traces appearing
1. **Check hooks are running:**
```bash
tail -f ~/.claude/state/braintrust_hook.log
```
2. **Verify environment variables** in `.claude/settings.local.json`:
- `TRACE_TO_BRAINTRUST` must be `"true"`
- `BRAINTRUST_API_KEY` must be valid
3. **Enable debug mode:**
```json
{
"env": {
"BRAINTRUST_CC_DEBUG": "true"
}
}
```
### Permission errors
Make hook scripts executable:
```bash
chmod +x /path/to/hooks/*.sh
```
### Missing jq command
Install jq:
- **macOS**: `brew install jq`
- **Ubuntu/Debian**: `sudo apt-get install jq`
### State issues
Reset the tracing state:
```bash
rm ~/.claude/state/braintrust_state.json
```
### Hook logs
View detailed hook execution logs:
```bash
# Follow logs in real-time
tail -f ~/.claude/state/braintrust_hook.log
# View last 50 lines
tail -50 ~/.claude/state/braintrust_hook.log
# Clear logs
> ~/.claude/state/braintrust_hook.log
```
## File structure
```
hooks/
├── common.sh # Shared utilities (logging, API, state)
├── session_start.sh # Creates root trace span
├── post_tool_use.sh # Captures tool calls
├── stop_hook.sh # Captures conversation turns
└── session_end.sh # Finalizes trace
```
## Alternative: SDK integration
For programmatic use with the Claude Agent SDK, use the native Braintrust integration:
```typescript
import { initLogger, wrapClaudeAgentSDK } from "braintrust";
import * as claudeSDK from "@anthropic-ai/claude-agent-sdk";
initLogger({
projectName: "my-project",
apiKey: process.env.BRAINTRUST_API_KEY,
});
const { query, tool } = wrapClaudeAgentSDK(claudeSDK);
```
See [Braintrust Claude Agent SDK docs](https://www.braintrust.dev/docs/integrations/sdk-integrations/claude-agent-sdk) for details.
© parcadei · MIT · parcadei/Continuous-Claude-v3