MoonMcp: Skill for Claude Code

.claude/skills/idea-gen/SKILL.md

idea-gen is a skill for Claude Code from Moonwuk/MoonMcp. It costs 163 tokens per session (3,105 once invoked), scanned A, original, MIT.

A skill for generating ideas in two separate situations: finding next security-testing hypotheses for a scoped target, or suggesting new MoonMCP capabilities. MoonMCP is the surrounding security-research toolset.

In plain words
What is it for?
Use it to decide what to test next on a known target or to propose additions to MoonMCP itself.
Why use it?
It bases suggestions on existing engagement or project information instead of mixing target testing with product planning.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is Moonwuk/MoonMcp's own configuration. It tells Claude Code how to work on MoonMcp 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 MoonMcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Moonwuk/MoonMcp. 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/Moonwuk/MoonMcp/main/.claude/skills/idea-gen/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Moonwuk/MoonMcp

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 idea-gen

README.md
[![agentmods](https://agentmods.dev/badge/skills/moonwuk/moonmcp/idea-gen.svg)](https://agentmods.dev/skills/moonwuk/moonmcp/idea-gen)
Your own site
<a href="https://agentmods.dev/skills/moonwuk/moonmcp/idea-gen"><img src="https://agentmods.dev/badge/skills/moonwuk/moonmcp/idea-gen.svg" alt="Measured on agentmods" height="20"></a>
Per session 163 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,105 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 $0.00163 $0.03105
Opus 5 $0.00081 $0.01553
Sonnet 5 $0.00033 $0.00621
Haiku 4.5 $0.00016 $0.00311

Measured 7d ago against content hash db3c5b4a35ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

idea-gen 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 7d ago.

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/idea-gen/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Idea generation skill

Two independent modes live here. Mode A brainstorms what to try next against a target already in this engagement. Mode B brainstorms what MoonMCP itself should grow next. Pick the mode by what's being asked about — a target/host name means Mode A, a capability/gap/research question means Mode B. Don't mix them: Mode A never proposes new tools, Mode B never touches a live target.

Mode A — Attack-vector brainstorming for a scoped target

Triggered by "what should I try next on <target>" / "brainstorm attack vectors for <target>". Output a ranked, non-redundant set of testable hypotheses grounded in this engagement's actual recon signal — never a generic checklist.

RECALL. Pull everything already known before touching the target again:

  • memory_brief(target) — one-shot rollup of entities, findings, leads, cross-target lessons.
  • memory_search(query=target, target=target) (add trust="curated" to skip unverified scraped noise) for anything memory_brief truncated.
  • memory_lesson(action="recall", query=target or the tech name) — prior tradecraft that might rule an approach in or out (e.g. a WAF that already eats a payload class here).
  • list_findings(target) — confirmed/labelled findings and their outcome (true_positive/false_positive/duplicate/wont_fix).

SIGNAL. Pull the entity graph rather than re-scanning: memory_graph(target) returns technology, service, endpoint, param, credential, cve, and asset nodes already discovered. Only when a needed signal is genuinely missing (no tech fingerprint, no endpoint list) recommend the one specific light-active tool that produces it — fingerprint, analyze_headers, tls_inspect, well_known, crawl, waf_detect, parse_openapi, discover_parameters — before hypothesizing further. Don't guess where a one-tool-call answer exists. (identify_waf is a separate, offline knowledge-base lookup — it matches text you already captured against vendor fingerprints and sends no traffic itself; reach for it in CROSS-REF alongside waf_info, not here.)

Read the full file on GitHub · 170 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. 7d ago First seen · 170 lines · 163 tokens per session scan A db3c5b4a35ed

Subscribe to this mod's changes

idea-gen is a skill published in the GitHub repository Moonwuk/MoonMcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 163 tokens to every session and 3,105 once invoked, about $0.0008 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

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…

microsoft/ai-agents-for-beginners · 200 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

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

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

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…

microsoft/vscode · 72 tokens