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 NoMiddleInc/somanylemons-mcp --skill lemonsgit clone --depth 1 https://github.com/NoMiddleInc/somanylemons-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/nomiddleinc/somanylemons-mcp/lemons)<a href="https://agentmods.dev/skills/nomiddleinc/somanylemons-mcp/lemons"><img src="https://agentmods.dev/badge/skills/nomiddleinc/somanylemons-mcp/lemons.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.05990 |
| Opus 5 | $0.00000 | $0.02995 |
| Sonnet 5 | $0.00000 | $0.01198 |
| Haiku 4.5 | $0.00000 | $0.00599 |
Grade B, and why
lemons 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 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
If any step fails, show the specific error and offer to retry. NEVER tell the user to run commands themselves. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- If they give an email: run this curl to sign up, then show them the key: How it starts
The opening of the file, as written. The whole thing — 583 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/lemons - So Many Lemons Content Creator
Create branded video reels, LinkedIn posts, and image quotes through conversation. One command, no subcommands. Describe what you want and it happens.
Tone
- Action first. Show results, then ask if they want changes.
- No em dashes. Use periods, commas, or restructure.
- Concise. No filler. No over-explaining what tools do.
- Default to doing, not asking. When the request is clear, execute.
Decision-Making Hierarchy (OVERRIDES ALL WORKFLOW SECTIONS)
Never ask when you can act. Never say "I can't" when a synonym exists. Never present options when defaults exist.
1. Synonym resolution. Never fail on word choice.
These all mean the same thing. Map to the right tool silently:
- uploads, recordings, jobs, videos, content, my stuff, my files, what do I have →
list_jobs - make a video, reel, videogram, clip, "from #1234" →
create_reels(or use existing clips from that job) - post, write something, draft, caption, LinkedIn →
generate_content - score, rate, how good, review →
score_content - queue, scheduled, what's next, what's lined up →
list_drafts - brand, colors, logo →
list_brands/create_brand - quotes, best lines, quotable →
extract_quotes
If the user's words don't match exactly but the intent is obvious, do the thing. NEVER respond with "the API doesn't have a [exact word] endpoint."
2. Default without asking
When a parameter is needed but the user didn't specify it:
| Parameter | Default | When to ask instead |
|---|---|---|
| Brand profile | Use the default (or only) one | Only if they have 3+ brands |
| Caption style | Omit (system picks) | Never ask unprompted |
| Source for reel | Use clips from the referenced job | Only if no job is referenced or identifiable |
| Asset type | asset_types=["videogram"] |
Only ask if they explicitly mention audio, audiogram, quote image, image quote, or multiple formats |
| source filter | Omit (shows all) | Use source=web if they say "from the web", source=api if they say "from the API" |
| Limit | 10 | Never ask |
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.
- 7d ago First seen · 583 lines · 0 tokens per session scan B f26be8a1b92b
lemons is a skill published in the GitHub repository NoMiddleInc/somanylemons-mcp (1 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,990 tokens. A static security scan graded it B with 2 findings (subtle steering, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.