session

A command-line tool for inspecting past AI coding-agent sessions. It lists recent sessions and shows details such as timing, model, turns, context use, tools, tokens, and costs.

In plain words
What is it for?
Use it to list recent sessions, inspect a chosen session, limit results, and return information in JSON for further processing.
Why use it?
It provides a structured way to understand what happened in earlier sessions without manually reviewing every conversation.

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/lanegrid/agtrace/session
Clone the repo
git clone --depth 1 https://github.com/lanegrid/agtrace
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 482 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 $0.00000 $0.00482
Opus 5 $0.00000 $0.00241
Sonnet 5 $0.00000 $0.00096
Haiku 4.5 $0.00000 $0.00048

Measured yesterday against content hash cf17537e8236, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

session 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 yesterday.

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.

docs/commands/session.md · 98 lines

What it actually says

agtrace session

Inspect and query historical AI coding agent sessions.

Overview

The session command provides tools to explore past sessions:

  • List recent sessions for the current project
  • Show detailed information about a specific session
  • Analyze session structure, turns, and metrics

Commands

session list

List recent sessions for the current project.

agtrace session list [OPTIONS]

Output includes:

  • Session ID
  • Start time
  • Duration
  • Model used
  • Turn count
  • Context usage

Options:

  • --format json - Output in JSON format for programmatic use
  • --limit N - Show only the N most recent sessions

Example:

agtrace session list --limit 10
agtrace session list --format json --limit 5

session show

Show detailed information about a specific session.

agtrace session show <SESSION_ID> [OPTIONS]

Output includes:

  • Session metadata (ID, timestamps, model)
  • Context window usage over time
  • Turn-by-turn breakdown
  • Tool usage summary
  • Token counts and costs

Options:

  • --format json - Output in JSON format

Example:

agtrace session show abc123def456
agtrace session show abc123def456 --format json > session.json

Use Cases

Compare Sessions

Compare two sessions to understand what changed:

agtrace session show session1 --format json > s1.json
agtrace session show session2 --format json > s2.json
diff s1.json s2.json

Debug Context Pressure

Identify when context pressure became an issue:

agtrace session show <SESSION_ID>
# Look for high context usage percentages in the output

Analyze Tool Usage

See which tools were called and when:

agtrace session show <SESSION_ID> --format json | jq '.turns[].steps[] | select(.type == "tool_call")'

See Also

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. yesterday First seen · 98 lines · 0 tokens per session scan A cf17537e8236

Subscribe to this mod's changes

session is a command published in the GitHub repository lanegrid/agtrace (59 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 482 tokens. 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.