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/wake/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/wake)<a href="https://agentmods.dev/skills/thunderkds/easy-ui-mcp/wake"><img src="https://agentmods.dev/badge/skills/thunderkds/easy-ui-mcp/wake/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/wake"><img src="https://agentmods.dev/badge/skills/thunderkds/easy-ui-mcp/wake.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 | $0.00083 | $0.01728 |
| Opus 5.5 | $0.00033 | $0.00691 |
| Sonnet 5.5 | $0.00017 | $0.00346 |
| Haiku 4.5 | $0.00008 | $0.00173 |
Grade A, and why
wake 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Cold-Start Orientation Specialist
You are the Supervisor running a structured cold-start orientation pass. Your single job is to read four live authoritative sources and emit a compact ≤50-line briefing covering recent changes, in-flight work, key memory decisions, and active learning records — so the Supervisor is fully oriented without opening any raw project file.
This skill is strictly read-only. It never writes, edits, or creates any file.
Karpathy Operational Commands
- Ask vs. Guess: Never infer project state — read the actual sources. If a source is missing, emit the specified degradation note and continue; never assume or fabricate content.
- Simplicity First: The briefing is a distilled snapshot, not a transcript. Show IDs and one-liners only. Do not reproduce full file contents.
- Surgical Changes: Read only the four designated sources. Do not modify MEMORY.md, LR files, KANBAN, or any other file — this skill has no Write or Edit steps.
- Goal-Driven Execution: Success = a coherent ≤50-line briefing covering all 4 sections is emitted in the conversation; the Supervisor is oriented without reading any raw file.
Workflow
Step 1 — Source Reads (attempt all four before composing output)
Read all four sources in parallel. If any source fails or is missing, record the fallback note for that section and continue — never halt or error.
| Source | How to read | Fallback if missing or empty |
|---|---|---|
| Git history | Run git log --oneline -10 via Bash tool |
"No git history found." (if no commits) or "Not a git repository." (if git fails) |
PROJECT_KANBAN.md |
Read full file, then filter to rows with status In Progress or 🔄 |
"No KANBAN found — project may be new or not yet planned." |
memory/MEMORY.md |
Read full file | "No MEMORY.md found." |
memory/learning-records/LR-*.md |
Read all .md files; keep only those with status: active in frontmatter; sort by filename descending; take top 3 |
"No active Learning Records yet." (same note if folder does not exist) |
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 · 137 lines · 83 tokens per session scan A 83221a5a2760
wake is a skill published in the GitHub repository thunderkds/easy-ui-mcp (1 stars, last pushed today), licensed MIT. It adds 83 tokens to every session and 1,728 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.
Other skills, from other repositories
git-ai-search
Search and restore AI conversation context from git history.
remember
Save the decisions, facts, dead ends and architecture this conversation established to Atlas's shared memory, so other agents and future sessions can build on them.
github-ops
GitHub CLI for issues, PRs, code search, CI logs, releases, and API queries. Requires gh CLI and auth.
release
Cut a Memoria release. Version bump, CHANGELOG, CI workflows, Docker image. Use when publishing a new version.
recall-rationale
Recall why a past change was made by locating the Claude Code transcript that produced it. Use when the user asks to "recall the rationale", "find the rationale", "look up the rationale", "why did I do X", "why did we do X", "why was this changed", or "find the transcript for this commit".
jolli-search
Search structured commit memories across all branches — decisions, topics, files. Use when the user wants to find prior decisions, related commits, or how a topic was handled before.