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.
curl -O https://raw.githubusercontent.com/thunderkds/easy-ui-mcp/main/.claude/skills/compact-advisor/SKILL.mdgit clone --depth 1 https://github.com/thunderkds/easy-ui-mcpWrote 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.
[](https://agentmods.dev/skills/thunderkds/easy-ui-mcp/compact-advisor)<a href="https://agentmods.dev/skills/thunderkds/easy-ui-mcp/compact-advisor"><img src="https://agentmods.dev/badge/skills/thunderkds/easy-ui-mcp/compact-advisor/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.
<a href="https://agentmods.dev/skills/thunderkds/easy-ui-mcp/compact-advisor"><img src="https://agentmods.dev/badge/skills/thunderkds/easy-ui-mcp/compact-advisor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00096 | $0.00913 |
| Opus 5.5 | $0.00038 | $0.00365 |
| Sonnet 5.5 | $0.00019 | $0.00183 |
| Haiku 4.5 | $0.00010 | $0.00091 |
Grade A, and why
compact-advisor 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Context Health Self-Assessor
You are the Supervisor running an honest, on-demand check of your own session health. This
operationalizes the "Self-monitoring for context overwhelm" rule in CLAUDE.md — that rule says
when to notice; this skill is the concrete, repeatable form the check takes once noticed, and the
form the user can invoke directly instead of waiting for you to notice.
Karpathy Operational Commands
- Ask vs. Guess: This is a judgment call based on observed session behavior, not a measurable token count — no tool exposes your own context size. Never claim a precise number; report what you actually observed.
- Simplicity First: One verdict, one reason, one recommended action. No score, no dashboard.
- Surgical Changes: This skill only produces a recommendation. It never calls
/compactorcompact-memoryitself — both are user-invoked; you cannot trigger either programmatically. - Goal-Driven Execution: Success = the user has a plain-language answer to "should we compact, and which kind?" — accurate enough to act on, in under 30 seconds of reading.
Workflow
1. Determine Trigger
- Automatic: you invoked this yourself because you noticed one of the signs in
CLAUDE.md's self-monitoring rule. Name which sign, concretely (e.g. "I had to re-read an earlier decision I should have already had in hand" — not just "context feels long"). - Manual: the user ran
/compact-advisor. No sign is assumed — assess fresh, and it's fine to conclude "looks fine, no action needed."
2. Assess — Two Separate Questions
These are different mechanisms with different scope. Answer both, independently:
a. Live conversation context (/compact territory — user-invoked only):
- Have you had to ask the user to re-state or re-confirm something from earlier this session?
- Has the user corrected the same kind of thing more than once?
- Is this session covering multiple unrelated tasks/topics end-to-end (a sign it's overdue for a fresh start rather than one continuous thread)?
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.
- yesterday First seen · 71 lines · 96 tokens per session scan A 25070e838d83
compact-advisor is a skill published in the GitHub repository thunderkds/easy-ui-mcp (1 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 913 once invoked, about $0.0004 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.
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…
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…
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…
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…
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.
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…