Bibliography

Primary Sources For Claude Logs

Annotated source list for Claude Code session logs, Agent SDK session storage, hooks, telemetry, and general log-management guidance.

#

Editorial rule

Primary sources first

Product behavior claims are grounded in Anthropic docs or the official changelog; general log-management claims use standards bodies and security guidance.

#

Secondary sources

Demand signals only

Community tools and posts can reveal search demand, but they are not used as authority for Claude product behavior.

"conversation history"

How To Use This Source List

Use Anthropic docs for current Claude Code and Agent SDK behavior. Use OpenTelemetry docs for vendor-neutral telemetry terminology. Use NIST and OWASP guidance for broader log-management and security-monitoring principles.

If a page on this site makes a claim about exact CLI flags, hook fields, transcript storage, telemetry attributes, or cost fields, verify it against the linked primary source before automating against it.

Source Index

The source cards below are intentionally compact. They are designed for both human reviewers and AI crawlers: title, publisher, URL, and the reason the source matters to the Claude Logs domain lane.

Primary sources

Sources behind this page

Anthropic

Work with sessions

Defines sessions as the conversation history accumulated while an agent works, and separates session state from filesystem state.

Anthropic

Manage sessions

Documents Claude Code transcript storage under ~/.claude/projects/<project>/<session-id>.jsonl and cautions that the entry format is internal and can change.

Anthropic

Claude Code monitoring

Reference for Claude Code metric names, event analysis, identity attributes, MCP audit detail, and retry analysis.

Anthropic

Hooks reference

Reference for hook lifecycle events, JSON input and output formats, and command, HTTP, prompt, and agent hooks.

Anthropic

CLI reference

Documents stream-json output, hook event inclusion, session persistence controls, naming, and resume flags.

Anthropic

Status line

Documents the JSON session data passed to status-line commands.

Anthropic

Track cost and usage

Explains per-step usage, model usage, session scoping, and the client-side nature of SDK cost estimates.

Anthropic

Claude pricing

Official model pricing table for input, output, cache write, and cache read tokens. Used by the token analyzer as a dated estimate table.

Anthropic

Todo Lists

Documents task/todo lifecycle and the migration from TodoWrite to structured task tools.

Anthropic

Claude Code changelog

Official changelog used for freshness checks on logging, session, hook, telemetry, and background-agent behavior.

OpenTelemetry

OpenTelemetry documentation

Defines OpenTelemetry as a vendor-neutral observability framework for traces, metrics, and logs.

NIST

NIST SP 800-92

Guide to computer security log management, including infrastructure and process planning.

OWASP

OWASP Top 10 A09:2021

Frames logging and monitoring failures as a detection, escalation, and response risk.

OWASP

OWASP Logging Cheat Sheet

Practical application logging guidance, including event design and verification considerations.

Cite this page

Claude Logs. "Primary Sources For Claude Logs." claudelogs.com, updated 2026-07-06. https://claudelogs.com/sources

FAQ

Why are some community tools not listed as sources?

They are useful for demand research, but the site cites primary docs for product behavior to reduce drift and unsupported claims.

What source should settle a dispute about Claude Code behavior?

Use current Anthropic documentation or the official Claude Code changelog first, then verify behavior in the installed version when automation depends on it.

Related evidence

Foundation

Session Logs

A source-grounded explanation of Claude Code and Agent SDK session logs, what they contain, and what they do not prove.

Field guide

Transcript Anatomy

How to read Claude JSONL transcript artifacts, hook transcript paths, subagent transcript paths, and stream-json output without mixing them up.

Telemetry

Observability

A practical map of Claude Code and Agent SDK telemetry: traces, metrics, logs, identity attributes, and event analysis.

Free tool

Log Viewer

Drop a Claude Code JSONL transcript and turn it into a readable local timeline of messages, tool calls, tool results, and token fields.

Free tool

Token Analyzer

Estimate Claude Code transcript token usage and cost by turn with a dated model pricing table and CSV export.

Free tool

Audit Checklist

Run an interactive agent-session audit checklist and export a concise Markdown note for PRs, incidents, and handoffs.