Skill

memory-tidy

Tidy memory files — extract oversized sections, detect stale counts

Install

Run in your terminal

npx claudepluginhub mistakeknot/interagency-marketplace --plugin intermem

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 6, 2026

Actions

View Source View Plugin View on GitHub View README

Memory Tidy

Structural housekeeping for auto-memory files. Extracts oversized sections from MEMORY.md into linked topic files and detects stale point-in-time counts.

Instructions

Running the Tidy

Find the intermem plugin install path and run the tidy subcommand:

INTERMEM_DIR="$(find ~/.claude/plugins/cache -path '*/intermem/*/pyproject.toml' -not -path '*/tests/*' -printf '%h\n' 2>/dev/null | sort -V | tail -1)"
cd "$INTERMEM_DIR" && uv run python -m intermem tidy --project-dir /path/to/project --json

Replace /path/to/project with the actual project directory.

Workflow

Dry-run first (default): Shows what would be extracted and which counts are stale
Review: Check the proposed extractions and stale counts
Apply: Run again with --apply to execute the extractions

# Dry-run
cd "$INTERMEM_DIR" && uv run python -m intermem tidy --project-dir /path/to/project

# Apply after review
cd "$INTERMEM_DIR" && uv run python -m intermem tidy --project-dir /path/to/project --apply

Options

--budget N — Maximum MEMORY.md line count (default: 120). Sections are extracted until under budget.
--section-threshold N — Minimum section size to consider for extraction (default: 15 lines). Smaller sections stay inline.
--apply — Execute changes. Without this flag, only shows a preview.
--json — Output results as JSON for programmatic consumption.

What It Does

Section extraction:

Parses MEMORY.md into sections by ## headings
Identifies sections exceeding --section-threshold lines
Extracts them to <slug>.md topic files in the same directory
Replaces sections with links in a ## Topic Files section
Never touches ## Quick Reference or ## Topic Files (protected)
Never clobbers existing topic files

Stale count detection:

Scans for patterns like 48 plugins, 94 tests, 15 skills
For directory-countable patterns (e.g., plugins → interverse/), checks actual count
Reports drift: "48 Interverse plugins" → actual: 52 (drift: +4)
Non-verifiable counts are flagged with [?]

When to Use

When MEMORY.md exceeds ~120 lines (the SessionStart hook will nudge you)
After a project grows significantly and counts become stale
Before running /intermem:synthesize — a tidy source produces better promotions