Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Memory Prune

ASecurity

Manual reviewable prune of stale memory entries. Lists project_* entries older than 30 days with content preview; Frank decides per-entry [keep | archive | pin]. Keeps MEMORY.md under the auto-load 200-line truncation. Use when MEMORY.md exceeds 180 lines or session-end after a heavy work week.

45 stars
0 votes
0 copies
0 views
Added 10/6/2026
ai-agentsgoshell

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 10/6/2026

$npx -y skills add frankxai/claude-skills-library --skill memory-prune --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Memory Prune?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Memory Prune
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/frankxai-memory-prune/badge)](https://www.skillsdirectory.com/skills/frankxai-memory-prune)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: memory-prune
description: Manual reviewable prune of stale memory entries. Lists project_* entries older than 30 days with content preview; Frank decides per-entry [keep | archive | pin]. Keeps MEMORY.md under the auto-load 200-line truncation. Use when MEMORY.md exceeds 180 lines or session-end after a heavy work week.
---

# Memory Prune — assisted, never autonomous

The memory system at `~/.claude/projects/C--Users-frank-Arcanea/memory/` accumulates ~2-3 entries/day. Once `MEMORY.md` exceeds ~200 lines the auto-loader truncates it and entries silently disappear from future-session context. This skill prevents that without auto-deleting things that might still matter.

## Philosophy

- **Never auto-delete.** Auto-decay is silent and corrupts the wisdom layer of memory.
- **Bias toward keeping `feedback`, `decision`, `reference`, `user`** — these are durable.
- **Bias toward pruning `project_*`** — these are session snapshots; old ones rarely re-load.
- **Always show content before deciding.** A 30-day-old project entry might be the one foundational decision you keep needing.

## How it works

1. Walks `~/.claude/projects/C--Users-frank-Arcanea/memory/` for `.md` files
2. Filters to `project_*.md` last-modified > N days ago (default 30)
3. For each candidate prints:
   - Filename + age in days
   - First 200 chars of body
   - Recommended action based on heuristics (see below)
4. Prompts Frank: `[k]eep | [a]rchive | [p]in | [s]kip`
5. Executes:
   - **archive** → move to `memory/archive/YYYY-MM/`, remove from `MEMORY.md`
   - **pin** → rename to `<original>_pinned.md`, ensure indexed in `MEMORY.md`
   - **keep** → no change (will resurface next prune)
   - **skip** → no change, no resurface this session

## Heuristic recommendations

| Pattern | Recommendation |
|---|---|
| `project_*_session_*.md` (session log) | archive — these are ephemeral by nature |
| `project_pp_audit_*.md` (PP audits) | archive after 60 days |
| `project_*_strategy.md` (strategy docs) | keep or pin — usually evergreen |
| `project_overnight_*.md` | archive — overnight session snapshots |
| `project_mega_session_*.md` | archive — date-bound sessions |
| `project_*_2026_03_*` | archive after 90 days |
| Any with content > 4 KB explaining a decision rationale | suggest pin |

## Invocation

Run via PowerShell in Windows:

```powershell
powershell -NoProfile -ExecutionPolicy Bypass -File "$env:USERPROFILE/.claude/skills/memory-prune/prune.ps1"
```

Or set up an alias in your shell:

```powershell
function prune-memory { & "$env:USERPROFILE/.claude/skills/memory-prune/prune.ps1" }
```

## What this skill does NOT do

- Does NOT delete files outright (only moves to archive/)
- Does NOT touch `feedback_*`, `decision_*`, `reference_*`, `user_*`
- Does NOT modify entries you skip
- Does NOT auto-trigger; only runs on explicit invocation

## Cadence recommendation

Run **once per month** or whenever `MEMORY.md` exceeds 180 lines (check via `wc -l MEMORY.md`).

## Decay-when

This skill itself decays only if memory architecture migrates (e.g., to a vector DB). At that point rebuild against the new substrate.

Attribution

frankxaifrankxai
View sourceSee grades on GitHubMore from frankxai →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →