skill-icon-workflow

skill-icon-workflow is a skill for Codex from btfranklin/skills. It costs 68 tokens per session (422 once invoked), scanned A, original, MIT.

A workflow for creating and checking icons used by coding-agent skills. It covers an editable SVG, a 100-by-100 PNG, and the icon references in the skill metadata.

In plain words
What is it for?
Use it to create, repair, export, validate, and visually inspect skill icons and their metadata paths.
Why use it?
It helps keep skill icons in the required formats, locations, and configuration while preserving their existing visual style.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex.

Good fit Use it to create, repair, export, validate, and visually inspect skill icons and their metadata paths.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/btfranklin/skills/skill-icon-workflow
Install

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.

Any agent
npx skills add btfranklin/skills --skill skill-icon-workflow
Clone the repo
git clone --depth 1 https://github.com/btfranklin/skills

Made for: Codex.

Wrote 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.

agentmods badge for skill-icon-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/btfranklin/skills/skill-icon-workflow.svg)](https://agentmods.dev/skills/btfranklin/skills/skill-icon-workflow)
Your own site
<a href="https://agentmods.dev/skills/btfranklin/skills/skill-icon-workflow"><img src="https://agentmods.dev/badge/skills/btfranklin/skills/skill-icon-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 422 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00068 $0.00422
Opus 5 $0.00034 $0.00211
Sonnet 5 $0.00014 $0.00084
Haiku 4.5 $0.00007 $0.00042

Measured 8d ago against content hash eb8e1e21a5bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

skill-icon-workflow 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 8d 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.

skills/skill-icon-workflow/SKILL.md · 36 lines

What it actually says

Skill Icon Workflow

Use this skill for the icon part of skill creation or maintenance. Also use skill-creator when the task changes skill instructions or other metadata.

Workflow

  1. Read references/icon-workflow.md for the asset and validation contract.
  2. Inspect the existing skill assets and agents/openai.yaml. Preserve the established visual identity when you repair or convert icons.
  3. Keep the editable design source and icon_small as SVG. Export icon_large from that source as a 100x100 PNG.
  4. Store both files in the target skill's assets/ directory. Use paths that are relative to the skill directory.
  5. Validate SVG structure, PNG format and dimensions, YAML syntax, file existence, and rendered appearance at small size.
  6. Limit metadata changes to icon fields unless the broader task explicitly includes metadata maintenance.

Use imagegen when the request requires new artwork or visual concepts. Do not use it only to convert files or update icon paths.

Verify Current Information

Before you change Codex metadata conventions, verify the current official skill-authoring guidance that is available in the environment. Record the convention or source when it changes the implementation. Do not treat an old local example as permanently authoritative.

Design Rules

  • Use a full-bleed background unless transparency is intentional.
  • Use simple silhouettes and strong contrast. Avoid details that disappear at small sizes.
  • Preserve gradients and alpha through export.
  • Never accept file extension alone as proof of format or dimensions.

Output

Report the files that you created or changed. Report the metadata paths, structural checks, image dimensions, and visual inspection result.

Files

What ships with it

5 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.

Changes

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.

  1. 8d ago First seen · 36 lines · 68 tokens per session scan A eb8e1e21a5bf

Subscribe to this mod's changes

skill-icon-workflow is a skill published in the GitHub repository btfranklin/skills (5 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 422 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 2026-08-31.