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 agentmods add skills/agentic-dev3o/devx-plugins/banana-logonpx skills add agentic-dev3o/devx-plugins --skill banana-logogit clone --depth 1 https://github.com/agentic-dev3o/devx-pluginsWhat 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 | $0.00061 | $0.00968 |
| Opus 5 | $0.00030 | $0.00484 |
| Sonnet 5 | $0.00012 | $0.00194 |
| Haiku 4.5 | $0.00006 | $0.00097 |
Grade A, and why
banana-logo 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 2d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Logo & Brand Identity
Input: $ARGUMENTS (optional — brand name, industry, and style direction)
If $ARGUMENTS is provided, use it as the brand brief and skip to prompt building. If empty, ask about the brand.
Requirements
uvinstalledGEMINI_API_KEYenvironment variable set (get one at https://aistudio.google.com/apikey)
Workflow
- Understand — Clarify the brand name, industry, personality adjectives (e.g., bold, playful, minimal), and any existing color palette or symbol preferences the user has.
- Build prompt — Compose a generation prompt following the Prompt Formula below, incorporating the user's brand attributes.
- Configure — Apply the Defaults (1:1, 1K, Pro model). Override only if the user explicitly requests a different setting.
- Generate — Run the script.
- Deliver — Report the saved file path. Do NOT read the image file back. Remind the user of the Text Caveat if letterforms are included. Offer to iterate.
Prompt Formula
[Brand Symbol/Shape] + [Static Balanced Pose] + [White Background] + [Centered Symmetric Composition] + [Minimal Flat Vector / Geometric]
Defaults
ALWAYS apply these unless the user explicitly overrides:
| Setting | Value |
|---|---|
| Aspect ratio | 1:1 |
| Resolution | 1K |
| Model | Pro |
Key Constraints
- Favicon test -- The logo must work at 16x16 px favicon size. Avoid fine details, thin strokes, and intricate ornamentation.
- Color limit -- Maximum 2-3 colors. Fewer colors reproduce better across media.
- White background -- Always include "on a white background" in the prompt for easy extraction and compositing.
- Shape language -- Angular shapes convey tech / aggressive energy. Rounded shapes convey friendly / approachable energy. Choose deliberately.
- TEXT CAVEAT -- Gemini is unreliable for exact letterforms. Warn the user: treat any text in the generated image as a visual concept only and recreate it in a proper vector tool (Figma, Illustrator, Inkscape) for final use.
What ships with it
1 file 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.
- 2d ago First seen · 95 lines · 61 tokens per session scan A a2c84c23e93f
banana-logo is a skill published in the GitHub repository agentic-dev3o/devx-plugins (11 stars, last pushed 14d ago), licensed MIT. It adds 61 tokens to every session and 968 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.