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/craft-spawn-prompt/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/craft-spawn-prompt)<a href="https://agentmods.dev/skills/thunderkds/easy-ui-mcp/craft-spawn-prompt"><img src="https://agentmods.dev/badge/skills/thunderkds/easy-ui-mcp/craft-spawn-prompt/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/craft-spawn-prompt"><img src="https://agentmods.dev/badge/skills/thunderkds/easy-ui-mcp/craft-spawn-prompt.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 | $0.00098 | $0.02471 |
| Opus 5.5 | $0.00039 | $0.00988 |
| Sonnet 5.5 | $0.00020 | $0.00494 |
| Haiku 4.5 | $0.00010 | $0.00247 |
Grade A, and why
craft-spawn-prompt 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Spawn Prompt Assembler
The single source of truth for turning a tasks/TASK_GUIDE_Txxx.md into a ready-to-paste Agent() prompt, so Stage 3 and the bugfix skill can't drift into two different checklists again. Consumes a guide path, produces text — it never calls the Agent tool itself, since skills run inline in the Supervisor's own context.
Karpathy Operational Commands (Specific Overrides)
- Ask vs. Guess: if the guide is missing a required field (
**Assigned agent**/**Agent guide**), stop and report the gap — do not guess an agent guide. - Surgical Changes: flag pre-flight problems in the assembled prompt; never silently rewrite the prompt to dodge the hook.
- Goal-Driven Execution: success is a fenced prompt block containing all required elements, plus a pass/flag verdict from the pre-flight check.
Workflow
1. Read inputs
Read the TASK_GUIDE at the given path, the .claude/agents/*.md file named in its **Agent guide** field, and memory/MEMORY.md. If any is missing, stop and report to the Supervisor.
2. Detect guide flavor
Search the guide for a ### Mental Model (or ## Mental Model) heading.
- Present → bugfix-flavored. Use the bugfix Step 4 shape.
- Absent → standard Stage-3-style. Use the standard shape.
3. Assemble the prompt
Both shapes reuse the same checklist proven in bugfix Step 4; only element 2 and the presence of element 3 change:
| # | Element | Standard guide | Bugfix-flavored guide |
|---|---|---|---|
| 1 | Guide pointer | tasks/TASK_GUIDE_Txxx.md path |
same |
| 2 | Orienting content | Guide's Restated Intent / Requirement section, verbatim | Confirmed Mental Model section, verbatim |
| 3 | First-action skill invocation | Only if the task explicitly requires one (e.g. migration-safety for schema work) — otherwise omit |
Skill({ skill: "diagnose" }) as the first action — always present |
| 4 | Memory reference | The path memory/MEMORY.md, with an instruction to read it in full. Do not paste its contents |
same |
| 5 | Agent-guide pointer | .claude/agents/<role>.md from the guide's **Agent guide** field |
same |
| 6 | Trace-attribution instruction | The active-task state-file line below, verbatim | same |
| 7 | Demonstration BEFORE-capture instruction | The BEFORE-capture line below, verbatim | same — for a bugfix guide, this is naturally satisfied by the Phase 1 repro loop the diagnose first action already builds; the instruction still restates the rule so the agent doesn't skip it under time pressure |
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 · 79 lines · 98 tokens per session scan A d761aed00db1
craft-spawn-prompt is a skill published in the GitHub repository thunderkds/easy-ui-mcp (1 stars, last pushed today), licensed MIT. It adds 98 tokens to every session and 2,471 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.