braintrust-tracing

braintrust-tracing is a skill for Claude Code from parcadei/Continuous-Claude-v3. It costs 20 tokens per session (3,126 once invoked), scanned B, original, MIT.

A guide for adding Braintrust tracing to Claude Code sessions, including links between a main session and its sub-agents. Tracing records what happened during a run so it can be inspected later.

In plain words
What is it for?
Use it to set up session and turn traces, record reads and edits, connect spawned sub-agents, and investigate Claude Code behavior.
Why use it?
It makes tool calls, edits, task spawning, and sub-agent activity easier to follow when debugging. Correlation helps show which child activity came from which parent session.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

Good fit Use it to set up session and turn traces, record reads and edits, connect spawned sub-agents, and investigate Claude Code behavior.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/parcadei/continuous-claude-v3/braintrust-tracing
About the project

Continuous-Claude-v3 is a Claude Code development environment that preserves working context between sessions, coordinates specialized agents, and stores project knowledge through ledgers, handoffs, and analysis tools. It is for people using Claude Code on ongoing or complex software work. Its catalogue entries are the skills, agents, hooks, plugin, and setting that provide its workflows and orchestration.

parcadei/Continuous-Claude-v3 · 3,937 stars · on GitHub

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.

Any agent
npx skills add parcadei/Continuous-Claude-v3 --skill braintrust-tracing
Clone the repo
git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3

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 braintrust-tracing

README.md
[![agentmods](https://agentmods.dev/badge/skills/parcadei/continuous-claude-v3/braintrust-tracing/github.svg)](https://agentmods.dev/skills/parcadei/continuous-claude-v3/braintrust-tracing)
Your own site
<a href="https://agentmods.dev/skills/parcadei/continuous-claude-v3/braintrust-tracing"><img src="https://agentmods.dev/badge/skills/parcadei/continuous-claude-v3/braintrust-tracing/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 braintrust-tracing

Your own site · 80×15
<a href="https://agentmods.dev/skills/parcadei/continuous-claude-v3/braintrust-tracing"><img src="https://agentmods.dev/badge/skills/parcadei/continuous-claude-v3/braintrust-tracing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,126 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 18 Mar 2026
  • Snyk warn 15 Feb 2026
How audits are shown
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 5.1 $0.00020 $0.03126
Opus 5 $0.00010 $0.01563
Sonnet 5 $0.00004 $0.00625
Haiku 4.5 $0.00002 $0.00313

Measured 10d ago against content hash ae25b7da1fbd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

braintrust-tracing scanned grade B with 1 finding 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 10d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

tail -f ~/.claude/state/braintrust_hook.log
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/skills/braintrust-tracing/SKILL.md · 368 lines

How it starts

The opening of the file, as written. The whole thing — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Braintrust Tracing for Claude Code

Comprehensive guide to tracing Claude Code sessions in Braintrust, including sub-agent correlation.

Architecture Overview

                         PARENT SESSION
                    +---------------------+
                    |  SessionStart       |
                    |  (creates root)     |
                    +----------+----------+
                               |
                    +----------v----------+
                    |  UserPromptSubmit   |
                    |  (creates Turn)     |
                    +----------+----------+
                               |
          +--------------------+--------------------+
          |                    |                    |
+---------v--------+  +--------v--------+  +--------v--------+
| PostToolUse      |  | PostToolUse     |  | PreToolUse      |
| (Read span)      |  | (Edit span)     |  | (Task - inject) |
+------------------+  +-----------------+  +--------+--------+
                                                    |
                                         +----------v----------+
                                         |   SUB-AGENT         |
                                         |   SessionStart      |
                                         |   (NEW root_span_id)|
                                         +----------+----------+
                                                    |
                                         +----------v----------+
                                         |   SubagentStop      |
                                         |   (has session_id)  |
                                         +---------------------+

Hook Event Flow

Hook Trigger Creates Key Fields
SessionStart Session begins Root span session_id, root_span_id
UserPromptSubmit User sends prompt Turn span prompt, turn_number
PreToolUse Before tool runs (modifies Task prompts) tool_input.prompt
PostToolUse After tool runs Tool span tool_name, input, output
Stop Turn completes LLM spans model, tokens, tool_calls
SubagentStop Sub-agent finishes (no span) session_id of sub-agent
SessionEnd Session ends (finalizes root) turn_count, tool_count

Read the full file on GitHub · 368 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. 10d ago First seen · 368 lines · 20 tokens per session scan B ae25b7da1fbd

Subscribe to this mod's changes

braintrust-tracing is a skill published in the GitHub repository parcadei/Continuous-Claude-v3 (3,937 stars, last pushed 7mo ago), licensed MIT. It adds 20 tokens to every session and 3,126 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

prove-checks

Prove a passing check was capable of failing before recording it as evidence. Use when a test, CI job, build-and-diff, smoke test or rehearsal comes back green and that green is about to be treated as proof - especially when the check depends on a setup mutation (a sed/awk rewrite, an env var, a secret, a fixture…

sergeyklay/.agents · 221 tokens

headsup-diagnose

Actively test the Codex headsup stack by flashing idle, working, and waiting tab colors and checking daemon application.

wasulajr/headsup · 30 tokens

headsup-status

Print a read-only health snapshot for the Codex headsup hook stack: daemon, watchdog, sessions, notifications, and logs.

wasulajr/headsup · 30 tokens

debugging-and-recovery

Use when something is broken, a test is failing, behavior is wrong, when investigating a production incident, when a user reports a bug, when a feature works locally but not in another environment, or when the system behaves differently than the contract specifies.

aneja5/forge-skills · 56 tokens

prod-debug

Production debugging skill. Pre-loads DB schema, container registry, and prod environment facts from .claude/prod-debug/ in the current project root. Use when the user invokes /prod-debug or /prod-debug bootstrap.

josephfung/trimkit · 48 tokens

error-handling-and-resilience

Use when establishing error handling patterns for a project, when adding retry logic, circuit breakers, or graceful degradation, when reviewing how a service handles failures, or when an incident reveals that a failure mode was silently swallowed.

aneja5/forge-skills · 50 tokens