md-cleanup

A command that audits Markdown instruction and memory files, including CLAUDE.md files, hook rules, skills, and stored notes. It produces one report about their context usage and maintenance needs.

In plain words
What is it for?
Running context-budget checks, reviewing Markdown rules and memory files, and finding candidates for maintenance; it is not intended to edit specific files or perform Git operations.
Why use it?
Large instruction files consume the limited context an agent can use for a task. The audit helps identify material that can be cleaned up or shortened.

Command

Part of the claude-ops-guard plugin — 2 commands, 5 hooks shipped together

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.

agentmods
npx agentmods add commands/nardovibecoding/simply-ops-guard/md-cleanup
Clone the repo
git clone --depth 1 https://github.com/nardovibecoding/simply-ops-guard

Or install claude-ops-guard, the plugin that ships this one along with the rest of its 2 commands, 5 hooks.

Per session 95 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,122 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 findings. Scan, not verified.
Origin unknown 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 $0.00095 $0.01122
Opus 5 $0.00048 $0.00561
Sonnet 5 $0.00019 $0.00224
Haiku 4.5 $0.00010 $0.00112

Measured 2d ago against content hash 83147419c3d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

md-cleanup scanned grade A with 2 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 2d 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.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat ~/.claude/hookify.*.local.md | wc -c

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Enumerates other installed skillslowAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

for f in $(find ~/.claude/skills -name "SKILL.md"); do awk '/^---/{n++; next} n==1{print}' "$f"; done | wc -c

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

commands/md-cleanup.md · 100 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 2d ago First seen · 100 lines · 95 tokens per session scan A 83147419c3d4

Subscribe to this mod's changes

md-cleanup is a command published in the GitHub repository nardovibecoding/simply-ops-guard (1 stars, last pushed 4mo ago), licensed AGPL-3.0. It adds 95 tokens to every session and 1,122 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 2 findings (reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.