Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jjmartres/ai-coding-agentsnpx agentmods add skills/jjmartres/ai-coding-agents/logo-designWrote 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/jjmartres/ai-coding-agents/logo-design)<a href="https://agentmods.dev/skills/jjmartres/ai-coding-agents/logo-design"><img src="https://agentmods.dev/badge/skills/jjmartres/ai-coding-agents/logo-design/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/jjmartres/ai-coding-agents/logo-design"><img src="https://agentmods.dev/badge/skills/jjmartres/ai-coding-agents/logo-design.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 | $0.00213 | $0.04195 |
| Opus 5.5 | $0.00085 | $0.01678 |
| Sonnet 5.5 | $0.00043 | $0.00839 |
| Haiku 4.5 | $0.00021 | $0.00419 |
Grade A, and why
logo-design 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 today.
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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Logo Design
You are acting as a senior identity designer. A logo is an identifier, not an explanation: a simple, distinctive, relevant mark that works at 16 px and on a building, in one colour, for decades. Your job is to find one clear idea, build it with craft, prove it works, and present it so it's judged on the right criteria.
Reply in the user's language. Keep the process visible but light: short explanations, real files, clear choices.
Pick the mode
| The user wants… | Mode | Start with |
|---|---|---|
| A new logo | Design (full or fast track below) | Phase 1 |
| Feedback on a logo | Critique | references/critique.md |
| To modernise/replace a logo | Redesign | references/redesign.md, then Design phases |
| Guidelines, sub-brands, patterns, motion | System | references/identity-system.md |
| Favicon/app icon/variants from an existing mark | Assets | scripts/export_variants.py |
Fast track (user wants results now, or gives little info): ask at most five questions in one message
(references/discovery-brief.md §2), or skip questions entirely, state your assumptions, and go straight to three
concepts. You can always iterate after they react.
Concept checkpoint — show the logos before building anything else. Every Design and Redesign run pauses after the concepts are built and tested (Phase 6): show the user the concept overview image, one line per concept and your recommendation, then offer the full logo kit and wait for their answer. Build the kit (Phase 7) only after they pick a direction and say yes. The kit is most of the work and only makes sense for an approved direction; showing concepts first lets the user steer cheaply and keeps them in control. Skip the pause only when the user explicitly says not to check in (e.g. "don't ask, just deliver everything"). If the user can't reply at all, stop at the checkpoint anyway and describe what the kit would contain.
Tools in this skill
All scripts are dependency-free Python 3 and live in the scripts/ folder next to this SKILL.md (in Claude Code
that is ${CLAUDE_SKILL_DIR}/scripts/; in other agents, use the folder this skill was loaded from). Run them with
python3 and the full path, e.g.
python3 <skill-dir>/scripts/svg_audit.py logo.svg (examples below write scripts/… for brevity).
On Windows, python3 is often the Microsoft Store stub; use python (or py -3) in every command instead.
What ships with it
60 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.
- assets/library/catalog.json 890 KB
- assets/library/classifications.json 549 KB
- assets/library/gallery.html 501 KB
- assets/library/stats.json 3.5 KB
- assets/library/svg/100tb.svg 3.8 KB
- assets/library/svg/500px.svg 3.0 KB
- assets/library/svg/active-campaign-icon.svg 1.4 KB
- assets/library/svg/active-campaign.svg 9.5 KB
- assets/library/svg/adonisjs-icon.svg 1.1 KB
- assets/library/svg/adonisjs.svg 8.3 KB
- assets/library/svg/adroll.svg 2.6 KB
- assets/library/svg/adyen.svg 1.5 KB
- assets/library/svg/aerospike-icon.svg 512 B
- assets/library/svg/aerospike.svg 5.7 KB
- assets/library/svg/airbnb.svg 3.3 KB
- assets/library/svg/airbrake.svg 3.2 KB
- assets/library/svg/airflow.svg 5.5 KB
- assets/library/svg/airtable.svg 1.4 KB
- assets/library/svg/akamai.svg 3.7 KB
- assets/library/svg/akka.svg 774 B
- assets/library/svg/alfresco.svg 5.3 KB
- assets/library/svg/algolia.svg 8.1 KB
- assets/library/svg/alpinejs-icon.svg 427 B
- assets/library/svg/alpinejs.svg 6.6 KB
- assets/library/svg/altair.svg 2.1 KB
- assets/library/svg/amazon-chime.svg 3.0 KB
- assets/library/svg/amazon-connect.svg 5.5 KB
- assets/library/svg/amex.svg 8.0 KB
- assets/library/svg/amp-icon.svg 1.3 KB
- assets/library/svg/amp.svg 5.0 KB
- assets/library/svg/ampersand.svg 3.9 KB
- assets/library/svg/amplication-icon.svg 484 B
- assets/library/svg/amplication.svg 4.1 KB
- assets/library/svg/amplitude-icon.svg 2.2 KB
- assets/library/svg/amplitude.svg 5.6 KB
- assets/library/svg/android-icon.svg 3.9 KB
- assets/library/svg/android.svg 7.3 KB
- assets/library/svg/angellist.svg 5.3 KB
- assets/library/svg/angular-icon.svg 734 B
- assets/library/svg/angular.svg 2.1 KB
- assets/library/svg/ansible.svg 3.8 KB
- assets/library/svg/ant-design.svg 3.2 KB
- assets/library/svg/apache_cloudstack.svg 9.3 KB
- assets/library/svg/apache-camel.svg 3.1 KB
- assets/library/svg/apache.svg 8.7 KB
- assets/library/svg/apiary.svg 1.9 KB
- assets/library/svg/apollostack.svg 1.1 KB
- assets/library/svg/apostrophe.svg 3.0 KB
- assets/library/svg/appbaseio-icon.svg 1.6 KB
- assets/library/svg/appbaseio.svg 6.3 KB
- assets/library/svg/appcircle-icon.svg 1.2 KB
- assets/library/svg/appcircle.svg 7.0 KB
- assets/library/svg/appcode.svg 2.0 KB
- assets/library/svg/appdynamics.svg 581 B
- assets/library/svg/appium.svg 870 B
- assets/library/svg/apple-app-store.svg 2.2 KB
- assets/library/svg/apple-pay.svg 2.2 KB
- assets/library/svg/apple.svg 1.0 KB
- assets/library/svg/appsignal-icon.svg 1.7 KB
- assets/library/svg/appsignal.svg 9.1 KB
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.
- today First seen · 237 lines · 213 tokens per session scan A 544bb2892874
logo-design is a skill published in the GitHub repository jjmartres/ai-coding-agents (48 stars, last pushed yesterday), licensed MIT. It adds 213 tokens to every session and 4,195 once invoked, about $0.0009 per session on Opus 5.5. 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 2026-10-20.
Other skills, from other repositories
review-a11y
Internal accessibility review pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit; not a menu entry. Checks the changed user-facing surface for accessibility: semantics, keyboard, focus, contrast, and ARIA correctness — applies only to user-facing surfaces. Findings only…
review-design
Internal UI/UX design review pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit; not a menu entry. Checks the changed UI against the project's design doc: consistency, states, responsiveness, and reuse — applies only when the project has a UI and the change touches it.…
ui-design-guidance
Canonical overlay for graphical UI or frontend redesign, polish-heavy implementation, and deep UX review; use ui-guidance for routine changes. Compose with matching implementation guidance when visual direction, accessibility, interaction, responsive behavior, forms, navigation, or data presentation need stronger…
design-md-author
Author, revise, or review visual DESIGN.md/design.md files, or explain an interface's visual rules without edits. Use source files, images, tokens, or a brief to document web, mobile, or desktop design decisions and reusable UI patterns. Excludes software architecture, UI implementation, and repository agent…
ui-guidance
Baseline overlay for routine graphical UI and frontend changes that preserve the existing design language; use ui-design-guidance for redesign, polish-heavy implementation, or deep UX review. Compose with matching implementation guidance. Not for terminal UIs or pure plotting.
cocoplus-config
CocoPlus configuration SSOT — $cocoplus sync propagates cocoplus.toml into downstream artifacts; $cocoplus migrate-config converts legacy safety-config.json. Invoked via $cocoplus sync and $cocoplus migrate-config.