cleanup

A maintenance tool for keeping two project-memory systems in agreement: Claude's MEMORY.md files and the ctx knowledge graph, which stores connected notes.

In plain words
What is it for?
Use it to inspect and reconcile project or global memory, remove duplicates, resolve conflicts, and keep MEMORY.md and ctx synchronized.
Why use it?
It finds duplicate, outdated, conflicting, or excessive notes before they make the agent's context unreliable. Changes require the user's approval.

Skill for Claude CodeCodex

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 skills/zate/cc-plugins/cleanup
Any agent
npx skills add Zate/cc-plugins --skill cleanup
Clone the repo
git clone --depth 1 https://github.com/Zate/cc-plugins

Made for: Claude Code, Codex.

Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,912 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00069 $0.01912
Opus 5 $0.00034 $0.00956
Sonnet 5 $0.00014 $0.00382
Haiku 4.5 $0.00007 $0.00191

Measured 2d ago against content hash 7e2299e99cfa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cleanup 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/analyze-sync.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/ctx/skills/cleanup/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ctx:cleanup — Memory Reconciliation

Reconcile Claude Code's built-in MEMORY.md system with the ctx knowledge graph. Detect duplicates, stale nodes, conflicts, and bloat across both systems, then resolve them with user approval.

Arguments

  • $1 — Project name (optional, auto-detected from git)
  • --global — Include all projects, not just the current one

Execution Flow

This is a phased command — run each phase in order, presenting findings to the user between phases.

Phase 1: Inventory

Gather the complete state of both memory systems.

Actions:

  1. Detect the current project name from git (basename $(git rev-parse --show-toplevel))
  2. Run the analysis script to dump both systems:
    sh "${CLAUDE_SKILL_DIR}/scripts/analyze-sync.sh" "$PROJECT"
    
  3. Read the MEMORY.md file for this project from ~/.claude/projects/ (search for directory matching project name)
  4. Read any supplemental memory files (*.md besides MEMORY.md in the same directory)
  5. Query ctx for all project-scoped nodes:
    ctx list --tag "project:$PROJECT" --format json
    
  6. Query ctx for global nodes (no project tag or project:global):
    ctx list --tag "project:global" --format json
    

If --global was passed, also inventory all other projects:

  • List all directories in ~/.claude/projects/*/memory/
  • List all unique project:* tags in ctx via ctx tags

Save the inventory mentally — it feeds all subsequent phases.

Phase 2: Analysis

Analyze the inventory for seven categories of issues. For each issue found, record: the issue type, affected items (node IDs / MEMORY.md line numbers), severity (high/medium/low), and recommended action.

Issue categories (consult references/sync-strategies.md for detailed detection patterns):

  1. Cross-system duplicates — Same knowledge in both MEMORY.md and ctx
    • Compare MEMORY.md content against pinned/working ctx nodes
    • Flag when semantically identical content exists in both
    • Severity: medium

Read the full file on GitHub · 198 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 198 lines · 69 tokens per session scan A 7e2299e99cfa

Subscribe to this mod's changes

cleanup is a skill published in the GitHub repository Zate/cc-plugins (10 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 1,912 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens