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 TreyDong/banana-skills --skill banana-skill-findergit clone --depth 1 https://github.com/TreyDong/banana-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/treydong/banana-skills/banana-skill-finder)<a href="https://agentmods.dev/skills/treydong/banana-skills/banana-skill-finder"><img src="https://agentmods.dev/badge/skills/treydong/banana-skills/banana-skill-finder/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/treydong/banana-skills/banana-skill-finder"><img src="https://agentmods.dev/badge/skills/treydong/banana-skills/banana-skill-finder.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 | $0.00183 | $0.01506 |
| Opus 5 | $0.00092 | $0.00753 |
| Sonnet 5 | $0.00037 | $0.00301 |
| Haiku 4.5 | $0.00018 | $0.00151 |
Grade B, and why
banana-skill-finder scanned grade B with 2 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 12d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls ~/.claude/skills/ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X GET "https://skillsmp.com/api/v1/skills/ai-search?q={natural_language_query}" \ How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Banana Skill Finder
Proactively helps users discover and install relevant Claude skills when they encounter tasks that could benefit from specialized capabilities.
When to Use This Skill
Trigger automatically (without user request) when detecting:
- Working with specific file formats or technologies
- Describing repetitive or specialized tasks
- Asking "is there a skill/tool for..." or similar
- Struggling with domain-specific work
- Any task where a specialized skill could help
Important: This skill should trigger proactively. Don't wait for users to explicitly ask for skill recommendations.
Workflow
1. Analyze User Need
Identify:
- Core task: What is the user trying to accomplish?
- Domain: What category does this fall into? (development, documents, data, web, devops, content, etc.)
- Keywords: Extract 2-4 relevant search terms
2. Search for Skills
Use a three-tier strategy with automatic fallback:
Tier 1: SkillsMP API (Best - if configured)
# Check for API key
echo $SKILLSMP_API_KEY
# If exists, use AI semantic search
curl -X GET "https://skillsmp.com/api/v1/skills/ai-search?q={natural_language_query}" \
-H "Authorization: Bearer $SKILLSMP_API_KEY"
Benefits:
- AI understands user intent, not just keywords
- Access to 60,000+ curated skills
- Best relevance and quality indicators
Tier 2: skills.sh WebFetch (Good - always works)
# Try search with query parameter
Use WebFetch: https://skills.sh/?q={keywords}
# Or browse leaderboard
Use WebFetch: https://skills.sh # All-time popular
Use WebFetch: https://skills.sh/trending # Trending (24h)
Benefits:
- 200+ high-quality curated skills
- No authentication needed
- Ranked by install count
- Shows trending skills
Tier 3: GitHub API (Fallback - may have limits)
curl -X GET "https://api.github.com/search/code?q={keywords}+SKILL.md+language:markdown" \
-H "Accept: application/vnd.github.v3+json"
Note: Rate limited (60/hour unauthenticated), use only as last resort.
What ships with it
3 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.
- 12d ago First seen · 188 lines · 183 tokens per session scan B 68f38b3f554c
banana-skill-finder is a skill published in the GitHub repository TreyDong/banana-skills (16 stars, last pushed 5mo ago), licensed MIT. It adds 183 tokens to every session and 1,506 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 2 findings (enumerates other installed skills, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…