aggregate-logs

aggregate-logs is a command for Claude Code from athola/claude-night-market. It costs 19 tokens per session (1,417 once invoked), scanned A, original, MIT.

A command that reads recorded skill-use logs and creates a LEARNINGS.md report. The report summarizes usage counts, success rates, timing, ratings, recurring problems, and suggested improvements over a chosen period.

In plain words
What is it for?
It is for reviewing skill performance, spotting high failure rates, slow runs, or low ratings, and collecting improvement ideas from recent logs.
Why use it?
It turns scattered execution records into a reviewable summary of which skills work well and where they cause friction.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is 0 9 * * MON cd /path/to/claude-night-market && ./plugins/abstract/scripts/aggregate_skill_logs.py 7.

Part of the abstract plugin — 16 skills, 17 commands, 5 agents, 4 hooks shipped together

Good fit It is for reviewing skill performance, spotting high failure rates, slow runs, or low ratings, and collecting improvement ideas from recent logs.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/athola/claude-night-market
agentmods
npx agentmods add commands/athola/claude-night-market/aggregate-logs

Made for: Claude Code.

Or install abstract, the plugin that ships this one along with the rest of its 16 skills, 17 commands, 5 agents, 4 hooks.

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 aggregate-logs

README.md
[![agentmods](https://agentmods.dev/badge/commands/athola/claude-night-market/aggregate-logs/github.svg)](https://agentmods.dev/commands/athola/claude-night-market/aggregate-logs)
Your own site
<a href="https://agentmods.dev/commands/athola/claude-night-market/aggregate-logs"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/aggregate-logs/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 aggregate-logs

Your own site · 80×15
<a href="https://agentmods.dev/commands/athola/claude-night-market/aggregate-logs"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/aggregate-logs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,417 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00019 $0.01417
Opus 5 $0.00010 $0.00709
Sonnet 5 $0.00004 $0.00283
Haiku 4.5 $0.00002 $0.00142

Measured 12d ago against content hash c98b1b9c9d6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

aggregate-logs 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 12d 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.

plugins/abstract/commands/aggregate-logs.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Aggregate Skill Execution Logs

Generate LEARNINGS.md from skill execution logs.

Usage

/abstract:aggregate-logs                    # Last 30 days (default)
/abstract:aggregate-logs --days 7           # Last 7 days
/abstract:aggregate-logs --days 90          # Last 90 days

Purpose

Part of Issue #69 Phase 3, this command processes skill execution logs to generate actionable insights for skill improvement.

What It Does

  1. Loads logs from ~/.claude/skills/logs/<plugin>/<skill>/
  2. Calculates metrics for each skill:
    • Execution count, success rate
    • Average/max duration
    • Average user rating (from evaluations)
    • Common friction points
    • Improvement suggestions
  3. Detects patterns:
    • High failure rates (>30%)
    • Slow execution (>10s average)
    • Low ratings (<3.5/5.0)
  4. Generates LEARNINGS.md at ~/.claude/skills/LEARNINGS.md

Output Format

LEARNINGS.md Structure

# Skill Performance Learnings

**Last Updated**: 2026-01-08 04:30:00 UTC
**Analysis Period**: Last 30 days
**Skills Analyzed**: 15
**Total Executions**: 342

## High-Impact Issues

### imbue:proof-of-work
**Type**: high_failure_rate
**Severity**: high
**Metric**: 42.3% success rate
**Detail**: 11/26 failures
**Recent Errors**:
- ValidationError: Missing acceptance_criteria field
- FileNotFoundError: PROOF.md not found
- KeyError: 'evidence' in evaluation

## Slow Execution

| Skill | Avg Duration | Max Duration | Executions |
|-------|--------------|--------------|------------|
| `sanctum:pr-agent` | 45.2s | 120.5s | 18 |
| `pensive:code-reviewer` | 32.1s | 89.3s | 24 |

## Low User Ratings

### abstract:skill-auditor - 2.8/5.0
**Common Friction**:
- Too verbose output
- Missing examples for modular skills
- Unclear token optimization guidance

**Improvement Suggestions**:
- Add --quiet flag
- Include example audits
- Link to token optimization docs

## Skill Performance Summary

| Skill | Executions | Success Rate | Avg Duration | Rating |
|-------|------------|--------------|--------------|--------|
| `imbue:proof-of-work` | 26 | 42.3% | 2.1s | 3.2/5.0 |
| `sanctum:pr-agent` | 18 | 94.4% | 45.2s | 4.5/5.0 |

Read the full file on GitHub · 193 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. 12d ago First seen · 193 lines · 19 tokens per session scan A c98b1b9c9d6c

Subscribe to this mod's changes

aggregate-logs is a command published in the GitHub repository athola/claude-night-market (337 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 1,417 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 2026-08-30.