analyze

A command for analyzing Claude Code session transcripts stored on your computer. It records events in a local SQLite database and reports agent behavior, tool use, token costs, and possible improvements.

In plain words
What is it for?
Use it to load all sessions or one session, generate reports, list session events, and run SQL queries on the stored data.
Why use it?
It helps you inspect how coding sessions actually ran instead of relying on memory. It can also mask common credential patterns before storing transcript data.

Command

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.

agentmods
npx agentmods add commands/josix/agent-flow/analyze
Clone the repo
git clone --depth 1 https://github.com/josix/agent-flow
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,065 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00015 $0.01065
Opus 5 $0.00008 $0.00532
Sonnet 5 $0.00003 $0.00213
Haiku 4.5 $0.00002 $0.00106

Measured 2d ago against content hash e8a024e4b5d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyze 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 2d 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.

commands/analyze.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze Command

Parse Claude Code session transcripts offline and surface subagent behavior metrics, tool usage patterns, token costs, and improvement opportunities — all stored in a local SQLite database with no network calls.

Arguments

  • --all-sessions (default for first run): Load all sessions from the auto-detected transcripts directory
  • --session <id>: Restrict loading to one session UUID
  • --report: Generate a full markdown report (default action after loading)
  • --sessions: List loaded sessions with event counts
  • --sql <query>: Run ad-hoc SQL against the events database
  • --transcripts-dir <path>: Override the auto-detected transcripts directory
  • --db <path>: Override the database path (default: .claude/observability/events.db)
  • --redact: Mask credential patterns (AWS keys, OpenAI keys, GitHub PATs) before storing

Workflow

FIRST RUN — Load transcripts and generate a report:

bash scripts/analyze.sh load --all-sessions
bash scripts/analyze.sh report

Or as a two-step invocation:

bash scripts/analyze.sh load --all-sessions && bash scripts/analyze.sh report

Inspect sessions:

bash scripts/analyze.sh sessions

Ad-hoc SQL:

bash scripts/analyze.sh sql "SELECT agent_type, COUNT(*) FROM events GROUP BY agent_type"

What You'll See

Report Sections

Section Description
Session Overview All loaded sessions with timestamps, branch, event count, subagent count
Tool Usage by Agent Which tools each agent called and how often
Skill / MCP Invocations MCP tool calls per agent (graphify, personal-kb, etc.)
Thinking Effort Thinking block count and character totals by agent
Token Usage Input/output/cache tokens by agent and model
Subagent Dispatches & Iteration Rate How many times each subagent type was dispatched per session
Rejection Rate Stop-hook block/approve/deny decisions per agent
Improvement Opportunities Automated heuristics (see below)

Read the full file on GitHub · 134 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. 2d ago First seen · 134 lines · 0 tokens per session scan A e8a024e4b5d3

Subscribe to this mod's changes

analyze is a command published in the GitHub repository josix/agent-flow (7 stars, last pushed 17d ago), licensed MIT. It adds 15 tokens to every session and 1,065 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-31.