easy-ui-mcp: Skill for Claude Code

.claude/skills/compact-memory/SKILL.md

compact-memory is a skill for Claude Code from thunderkds/easy-ui-mcp. It costs 69 tokens per session (1,141 once invoked), scanned A, original, MIT.

A memory-maintenance skill that reviews a project's two-level memory system, with a short index and longer reference files. It finds stale or duplicated entries and prepares approved consolidations without deleting unapproved information.

In plain words
What is it for?
Use it when memory files exceed their intended size, contain duplicates, or feel cluttered to review cold files, flag changes, and resync the MEMORY.md index.
Why use it?
Project memory becomes harder to use when it grows too large or contains outdated notes. This keeps the quick index and detailed files more accurate while preserving human control over deletion.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is thunderkds/easy-ui-mcp's own configuration. It tells Claude Code how to work on easy-ui-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything easy-ui-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to thunderkds/easy-ui-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/thunderkds/easy-ui-mcp/main/.claude/skills/compact-memory/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/thunderkds/easy-ui-mcp

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 compact-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/thunderkds/easy-ui-mcp/compact-memory/github.svg)](https://agentmods.dev/skills/thunderkds/easy-ui-mcp/compact-memory)
Your own site
<a href="https://agentmods.dev/skills/thunderkds/easy-ui-mcp/compact-memory"><img src="https://agentmods.dev/badge/skills/thunderkds/easy-ui-mcp/compact-memory/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 compact-memory

Your own site · 80×15
<a href="https://agentmods.dev/skills/thunderkds/easy-ui-mcp/compact-memory"><img src="https://agentmods.dev/badge/skills/thunderkds/easy-ui-mcp/compact-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,141 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 $0.00069 $0.01141
Opus 5.5 $0.00028 $0.00456
Sonnet 5.5 $0.00014 $0.00228
Haiku 4.5 $0.00007 $0.00114

Measured yesterday against content hash b00cb624d57a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

compact-memory 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 yesterday.

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/skills/compact-memory/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role: Memory Compaction Specialist

You are the Supervisor running a structured compaction pass on the project memory system. The goal is to keep the hot tier lean (≤50,000 characters) and the cold files accurate — without deleting anything the human hasn't approved.

Karpathy Operational Commands

  • Ask vs. Guess: Never delete an entry without explicit human approval. Flag, present, wait.
  • Simplicity First: Compact only what is clearly stale or duplicated. Do not reorganise sections speculatively.
  • Surgical Changes: Touch only memory/ files. Do not modify CLAUDE.md, task guides, or any other file.
  • Goal-Driven Execution: Success = cold file line counts reduced, hot-tier index accurate, zero unapproved deletions.

Workflow

1. Size Check

Run:

wc -l memory/decisions.md memory/glossary.md memory/learnings.md memory/MEMORY.md

Report the counts. Flag any cold file exceeding 500 lines as a compaction candidate. If all files are under 500 lines and the user still invoked this skill, note it and ask if they want to proceed anyway.

2. Stale Detection

For each entry in each cold file, check all of the following heuristics:

a. Dead file reference — does the entry cite a file path? If yes:

# for each cited path, e.g.:
ls memory/decisions.md   # or use Glob

If the file no longer exists → mark <!-- STALE: file deleted --> inline.

b. Outdated library version — does the entry mention a library + version? Cross-check:

# e.g. grep the version in package.json / pyproject.toml / go.mod
grep -r "library-name" package.json pyproject.toml go.mod 2>/dev/null | head -5

If the project has since upgraded past the version in the entry → mark <!-- STALE: version upgraded -->.

c. Duplicate — is the same fact stated under two different entries or sections? Mark the older/vaguer one <!-- STALE: duplicate of [other entry] -->.

d. Superseded — is there a newer entry in the same section that contradicts this one? Mark the older one <!-- STALE: superseded by [newer entry date] -->.

Read the full file on GitHub · 97 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. yesterday First seen · 97 lines · 69 tokens per session scan A b00cb624d57a

Subscribe to this mod's changes

compact-memory is a skill published in the GitHub repository thunderkds/easy-ui-mcp (1 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 1,141 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-30.

Related

Other skills, from other repositories

knowledge-ingest

Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, source notes, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn), including the Learn from conversations and Learn from Memory…

openclaw/openclaw · 80 tokens

forget

Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…

asgeirtj/system_prompts_leaks · 74 tokens

mem0-oss-to-platform

Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…

mem0ai/mem0 · 217 tokens

Cortex

LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…

danielmiessler/LifeOS · 184 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens