logs-summary

A command that reads agent-monitor logs and summarizes sessions, errors, performance, and loops. Logs are records of what the agents and tools did while a session was running.

In plain words
What is it for?
Use it to inspect the latest session, review all sessions, filter for errors or performance, investigate loop warnings, or analyze one session by ID.
Why use it?
It saves you from reading many log files by hand and helps reveal failures, slow operations, or repeated activity.

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/jonase47/ccpr/logs-summary
Clone the repo
git clone --depth 1 https://github.com/jonase47/ccpr
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 624 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 $0.00624
Opus 5 $0.00000 $0.00312
Sonnet 5 $0.00000 $0.00125
Haiku 4.5 $0.00000 $0.00062

Measured yesterday against content hash 9fc751d6e789, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

logs-summary 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.

commands/logs-summary.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/logs-summary

Analyzes and summarizes the agent monitor logs.

Argument: $ARGUMENTS = [focus or session ID]

Possible arguments:

  • No argument: Summary of the last session
  • all: Overview of all sessions
  • errors: Show errors only
  • performance: Performance data only
  • loops: Loop warnings and blockings only
  • {session-id}: Analyze a specific session

Execution

1. Locate log files

Check the following directories:

  • ~/.claude/logs/sessions/ – Session-based logs
  • ~/.claude/logs/activity.jsonl – Aggregated activity log
  • ~/.claude/logs/errors.jsonl – Aggregated error log
  • ~/.claude/logs/performance.jsonl – Aggregated performance log

If no logs are present, report this to the user.

2. Analysis by focus

Default (last session):

Read the most recent session from ~/.claude/logs/sessions/ and create:

  • Session overview: Start, end, duration, reason for termination
  • Agent activity: Which agents ran, how long, how many tool calls
  • Errors: All errors with timestamp and context
  • Loop events: Warnings and blockings
  • Performance: Top 5 slowest tool calls, top 5 slowest agents
all (all sessions):

Read ~/.claude/logs/activity.jsonl and create:

  • Table of all sessions: ID, date, duration, number of tool calls, error count
  • Sorted by date (newest first)
  • Maximum the last 20 sessions
errors (errors only):

Read ~/.claude/logs/errors.jsonl and show:

  • All errors grouped by type (ToolFailure, LoopWarning, LoopBlocked, etc.)
  • With timestamp, affected tool, error message
  • Sorted by frequency
performance (performance only):

Read ~/.claude/logs/performance.jsonl and show:

  • Average duration per agent
  • Average duration per tool type
  • Slowest individual calls
  • Total tool calls per session
loops (loop events only):

Filter from ~/.claude/logs/errors.jsonl only events of type LoopWarning and LoopBlocked:

  • Which tool, how many repetitions, when
  • Recognize patterns: which tools loop most frequently?

Read the full file on GitHub · 73 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. yesterday First seen · 73 lines · 0 tokens per session scan A 9fc751d6e789

Subscribe to this mod's changes

logs-summary is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 624 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 2026-08-31.