Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add nataliacorrea03/claude-code-skills --skill meta-promptgit clone --depth 1 https://github.com/nataliacorrea03/claude-code-skillsWrote 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/nataliacorrea03/claude-code-skills/meta-prompt)<a href="https://agentmods.dev/skills/nataliacorrea03/claude-code-skills/meta-prompt"><img src="https://agentmods.dev/badge/skills/nataliacorrea03/claude-code-skills/meta-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/nataliacorrea03/claude-code-skills/meta-prompt"><img src="https://agentmods.dev/badge/skills/nataliacorrea03/claude-code-skills/meta-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 | $0.00264 | $0.01574 |
| Opus 5 | $0.00132 | $0.00787 |
| Sonnet 5 | $0.00053 | $0.00315 |
| Haiku 4.5 | $0.00026 | $0.00157 |
Grade A, and why
meta-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 11d 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.
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.
Meta AI Prompt Builder
What this is
Muse Spark (Meta AI, used at meta.ai) can read public Instagram, Threads, and Facebook content directly, which Claude cannot. But it is a closed chat app with no API or MCP, so Claude cannot run it. This skill does the next best thing: it interviews the user about their research goal, picks the right prompt from the library, fills in the specifics, and hands back a strong, paste-ready prompt to run inside meta.ai.
Output is always a prompt for the user to paste into meta.ai. This skill never fetches Instagram data itself and never pretends to.
Grounded capabilities (do not exceed these)
Only build prompts around capabilities Muse Spark actually has:
- Reading and semantic search over public Instagram, Threads, and Facebook posts (content since Jan 2025)
- Finding creators by niche, topic, location, and follower count
- Reading captions, comments, and engagement to surface trends
- Studying a creator's feed and voice
- Finding brand mentions across the three platforms
If a user's goal needs something outside this list (TikTok or YouTube, guaranteed exact view/engagement numbers, scheduling, posting, anything on private accounts), say so plainly and offer the closest grounded prompt instead. Do not invent a capability to satisfy the request. Every generated prompt already forces meta.ai to self-report what it cannot do, which is the honest backstop.
The library
The prompt templates live in prompts/library.md. Read it when this skill runs. Current entries:
| ID | Use case |
|---|---|
| A1 | Micro-influencer / ambassador finder |
| A2 | Existing-fan creator finder (already posted about the brand) |
| A3 | Handle verification + profile snapshot |
| B1 | Reaction / stitch target finder (videos to react to) |
| B2 | Niche trend scan |
| B3 | Saturation & gap check |
| B4 | Comment mining (audience questions and pain) |
| C1 | Brand mention monitor |
| C2 | Competitor account teardown |
| D1 | Creator voice study before a pitch |
| E1 | Hook Machine (full multi-turn workflow, delivered whole, not variable-filled) |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 71 lines · 264 tokens per session scan A 28f8ba1fdbc5
meta-prompt is a skill published in the GitHub repository nataliacorrea03/claude-code-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 264 tokens to every session and 1,574 once invoked, about $0.0013 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.
Other skills, from other repositories
mle-workflow
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.
autonomous-loops
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
react-patterns
React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.
content-engine
Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
agent-carnet
Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.