memory-file-maintenance

memory-file-maintenance is a cursor rule for Cursor from mohitagw15856/pm-claude-skills. It costs 141 tokens per session (1,089 once invoked), scanned A, original, MIT.

A maintenance guide for AI memory and context files such as MEMORY.md, CLAUDE.md, or custom instructions. It checks their contents and keeps them current.

In plain words
What is it for?
Use it to review, prune, clarify, and update AI instructions, resolve conflicts, check privacy risks, and establish a light maintenance routine.
Why use it?
These files can become outdated, bloated, contradictory, or contain information that should not be retained.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc). Also seen: mentions CLAUDE.md.

Good fit Use it to review, prune, clarify, and update AI instructions, resolve conflicts, check privacy risks, and establish a light maintenance routine.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/mohitagw15856/pm-claude-skills/memory-file-maintenance
About the project

PM Skills is a collection of plain-Markdown instructions that teach AI assistants structured methods for handling professional, personal, and life-admin tasks. People use it with Claude, ChatGPT, Gemini, Cursor, Codex, and other supported agents for work such as writing product requirements, reviewing documents, or planning difficult situations.

mohitagw15856/pm-claude-skills · 1,352 stars · on GitHub · mohitagw15856.github.io

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.

Clone the repo
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills

Made for: Cursor.

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 memory-file-maintenance

README.md
[![agentmods](https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/memory-file-maintenance/github.svg)](https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/memory-file-maintenance)
Your own site
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/memory-file-maintenance"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/memory-file-maintenance/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 memory-file-maintenance

Your own site · 80×15
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/memory-file-maintenance"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/memory-file-maintenance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 141 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,089 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 $0.00141 $0.01089
Opus 5 $0.00071 $0.00544
Sonnet 5 $0.00028 $0.00218
Haiku 4.5 $0.00014 $0.00109

Measured 7d ago against content hash 00335cc6e2a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

memory-file-maintenance 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 7d 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.

exports/cursor/pm-ai-native/memory-file-maintenance/memory-file-maintenance.mdc · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory-File Maintenance

A personal AI memory file (MEMORY.md, CLAUDE.md, custom instructions) is only as good as it is current — over time it bloats with stale rules, contradicts itself, and drifts from who you actually are now. This tends it: reviews what's there, prunes the dead weight, sharpens the vague, adds the new patterns worth keeping, and sets a light maintenance habit — so your AI keeps understanding the real you. It also re-checks the privacy line on what should never be in there.

What This Skill Produces

  • A health review — what in the current file is stale, contradictory, bloated, redundant, or vague — and what important context is missing
  • Prune & sharpen edits — removing dead rules and tightening vague ones into clear, actionable statements
  • Additions — new patterns, preferences, and lessons worth adding from how you've actually been working/deciding lately
  • A conflict check — surfacing and resolving instructions that contradict each other (which confuse the AI)
  • A privacy re-check — confirming no credentials, financial, health, or others' personal data has crept in
  • A maintenance habit — a light cadence (a quick review every so often, add-a-line-as-you-go) so it stays current

Required Inputs

Ask for these if not provided:

  • The current file — your MEMORY.md / CLAUDE.md / custom instructions (paste it)
  • What's changed — how your work, preferences, or life have shifted since you wrote it
  • Any friction — where the AI has been getting you wrong lately (a clue to what's stale/missing)
  • New patterns — recent rules, lessons, or preferences worth capturing

Framework: Prune, Sharpen, Add, Protect

  1. Review against reality. Compare what's in the file to who the person actually is now — files drift as people change.
  2. Prune the dead weight. Remove stale rules, resolved situations, and redundancy — a bloated file dilutes the important stuff and confuses the AI.
  3. Sharpen the vague. Turn fuzzy statements into clear, actionable ones ("be concise" → "lead with the answer, then reasoning") so they actually work.
  4. Resolve contradictions. Surface instructions that conflict (a common cause of inconsistent AI behavior) and pick one.
  5. Add what's missing. Capture new preferences, patterns, and lessons from how the person's actually been working — the file should grow with them.
  6. Re-check privacy. Confirm nothing sensitive (credentials, financial, health, others' personal info) has crept in — and remove it if so.
  7. Set a light habit. A quick periodic review plus adding a line when a new pattern emerges keeps it current without being a chore.

Read the full file on GitHub · 70 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. 7d ago First seen · 70 lines · 141 tokens per session scan A 00335cc6e2a3

Subscribe to this mod's changes

memory-file-maintenance is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,352 stars, last pushed 3d ago), licensed MIT. It adds 141 tokens to every session and 1,089 once invoked, about $0.0007 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 2026-09-03.