Skill

report

engram: Generate a token savings report showing compression and redundancy statistics for the current session

Install

Run in your terminal

npx claudepluginhub pythondatascrape/engram-ccode --plugin engram

Tool Access

This skill uses the workspace's default tool permissions.

Skill Content

Similar Skills

cache-components

Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.

cache-components

138.6k

claude-opus-4-5-migration

2 files

Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.

claude-opus-4-5-migration

83.2k

evaluation-methodology

1 file

Details PluginEval's skill quality evaluation: 3 layers (static, LLM judge), 10 dimensions, rubrics, formulas, anti-patterns, badges. Use to interpret scores, improve triggering, calibrate thresholds.

plugin-eval

32.9k

Stats

Stars0

Forks0

Last CommitMar 28, 2026

Actions

View Source View Plugin View on GitHub View README

Steps

Call mcp__engram__get_stats with no arguments to retrieve the current session statistics.

Present the stats summary to the user, then ask:

Report name — suggest the default: Session Report — {today's date} (e.g. "Session Report — 2026-03-27")
Description (optional) — a brief note about this session (press Enter to skip)
Save to savings log? — whether to append a row to .engram/savings-log.csv (default: yes)

Check if .engram/config.yaml exists. If it does, read it and extract any pricing fields (pricing.model, pricing.input_per_1k). Pass those as arguments when calling the report tool.

Call mcp__engram__generate_report with:

name: the report name the user provided
description: the description the user provided (omit if blank)
savingsLogPath: if user said yes to saving, pass .engram/savings-log.csv; omit if they said no
pricing: if config has pricing info, pass as { "model": "...", "inputPer1k": ... } (nested object)

Display the full markdown report returned by the tool.

Ask: "Would you like to save this report as a markdown file?" If yes, ask for a filename (suggest engram-report-{date}.md) and write the report to that path in the current working directory.

Engram Report

Generate a token savings report for the current session.

Steps

Call mcp__engram__get_stats with no arguments to retrieve the current session statistics.
Present the stats summary to the user, then ask:
- Report name — suggest the default: Session Report — {today's date} (e.g. "Session Report — 2026-03-27")
- Description (optional) — a brief note about this session (press Enter to skip)
- Save to savings log? — whether to append a row to .engram/savings-log.csv (default: yes)
Check if .engram/config.yaml exists. If it does, read it and extract any pricing fields (pricing.model, pricing.input_per_1k). Pass those as arguments when calling the report tool.
Call mcp__engram__generate_report with:
- name: the report name the user provided
- description: the description the user provided (omit if blank)
- savingsLogPath: if user said yes to saving, pass .engram/savings-log.csv; omit if they said no
- pricing: if config has pricing info, pass as { "model": "...", "inputPer1k": ... } (nested object)
Display the full markdown report returned by the tool.
Ask: "Would you like to save this report as a markdown file?" If yes, ask for a filename (suggest engram-report-{date}.md) and write the report to that path in the current working directory.