memory-hygiene

memory-hygiene is a command for Claude Code from adamwstauffer/shidler. It costs 0 tokens per session (322 once invoked), scanned A, original, MIT.

A periodic maintenance command for the coding agent's saved memory files, including the MEMORY.md index and individual fact files.

In plain words
What is it for?
Run it every several sessions, before shortening a conversation, or after adding memories to validate links, triage problems, and organise the index.
Why use it?
Saved notes can accumulate broken links, missing details, duplicates, or outdated information, making future sessions less reliable.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

Good fit Run it every several sessions, before shortening a conversation, or after adding memories to validate links, triage problems, and organise the index.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/adamwstauffer/shidler/memory-hygiene
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/adamwstauffer/shidler

Made for: Claude Code.

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-hygiene

README.md
[![agentmods](https://agentmods.dev/badge/commands/adamwstauffer/shidler/memory-hygiene.svg)](https://agentmods.dev/commands/adamwstauffer/shidler/memory-hygiene)
Your own site
<a href="https://agentmods.dev/commands/adamwstauffer/shidler/memory-hygiene"><img src="https://agentmods.dev/badge/commands/adamwstauffer/shidler/memory-hygiene.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 322 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 $0.00000 $0.00322
Opus 5 $0.00000 $0.00161
Sonnet 5 $0.00000 $0.00064
Haiku 4.5 $0.00000 $0.00032

Measured 8d ago against content hash a6182d99101c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

memory-hygiene 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 8d 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.

.claude/commands/memory-hygiene.md · 23 lines

What it actually says

/memory-hygiene — Validate + organize the memory store

Run periodically (every ~10 sessions), before a /compact, or after a session that wrote new memories. Keeps the Claude auto-memory store (MEMORY.md index + single-fact *.md files) coherent as it grows.

What this command does

Follow the methodology in .claude/skills/memory-hygiene/SKILL.md end-to-end:

  1. Run .claude/skills/memory-hygiene/validate_memory.py against ~/.claude/projects/C--GitHub-shidler/memory.
  2. Triage findings — errors (broken index links, missing name: frontmatter) get fixed; warnings (orphans, dangling [[refs]], missing description/type) get fixed opportunistically or explained.
  3. If MEMORY.md is crowded (>~25 lines), group the index by type (feedback_* together, project_* together) without editing fact content.

Guardrails

  • MEMORY.md is an index — one line per memory, pointer only, never fact content.
  • A dangling [[ref]] is only a bug if it's a typo or points at a non-memory doc; deliberate forward-refs are allowed.
  • Delete memories that are wrong; don't store what the repo already records.

Output

The validator's findings, triaged, ending with: Memory hygiene: <N> memories / <E> errors / <W> warnings — <fixed / routed>.

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. 8d ago First seen · 23 lines · 0 tokens per session scan A a6182d99101c

Subscribe to this mod's changes

memory-hygiene is a command published in the GitHub repository adamwstauffer/shidler (10 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 322 tokens. 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 2026-08-31.