update-badges

A command that adds or updates shields.io badges in plugin README files. It can inspect plugin metadata and files to choose badges for languages, licenses, repositories, and detected tools.

In plain words
What is it for?
Use it to update one plugin's badges or scan all plugin folders for badge changes. It helps document languages such as Python, Node.js, TypeScript, and Bash, plus detected services such as Gemini.
Why use it?
It removes the manual work of checking each plugin and keeping its README badges accurate. It also avoids having to remember which project files indicate which badges.

Command for Claude Code

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.

agentmods
npx agentmods add commands/reggiechan74/cc-plugins/update-badges
Clone the repo
git clone --depth 1 https://github.com/reggiechan74/cc-plugins

Made for: Claude Code.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,367 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00011 $0.01367
Opus 5 $0.00005 $0.00683
Sonnet 5 $0.00002 $0.00273
Haiku 4.5 $0.00001 $0.00137

Measured 2d ago against content hash e73a8e91708d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update-badges 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.

.claude/commands/update-badges.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Badges

Add or update shields.io badges on plugin README files.

Arguments received: $ARGUMENTS

Instructions

Step 1: Determine Targets

If $ARGUMENTS is provided, treat it as a plugin folder name (e.g., nano-banana-plugin). Validate that /workspaces/claude-plugins/$ARGUMENTS/.claude-plugin/plugin.json exists.

If $ARGUMENTS is empty, scan for all plugin directories by globbing */.claude-plugin/plugin.json under /workspaces/claude-plugins/. Exclude .git, .claude, .claude-plugin, node_modules, docs, and hidden directories.

Step 2: Auto-Detect Badges for Each Plugin

For each target plugin folder, read the following files to detect applicable badges:

  1. Read .claude-plugin/plugin.json — extract name, version, license, repository, keywords
  2. Read README.md — note existing badges (lines containing img.shields.io)
  3. Read LICENSE — if present, confirm license type from first line
  4. Scan for language signals:
    • Python files (*.py) → Python badge
    • package.json → Node.js badge
    • *.ts files → TypeScript badge
    • *.sh files only → Bash badge
  5. Scan skill files for API keywords:
    • "Gemini" → powered_by-Gemini_API-orange
    • "OpenAI" → powered_by-OpenAI-412991
    • "Google" (Calendar, Gmail, etc.) → Google_Workspace-4285F4
    • "ArcGIS" or "Esri" → ArcGIS-2C7AC3
  6. Always include: Claude Code plugin badge (Claude_Code-plugin-blueviolet)

Build a candidate list of badges. Each badge has:

  • label: Display name (e.g., "Version", "License: MIT")
  • url: Full shields.io markdown (e.g., ![Version](https://img.shields.io/badge/version-1.0.0-blue))
  • detected: Whether it was auto-detected (true) or an optional addition

Step 3: Present Badge Choices

Use AskUserQuestion with multiSelect: true to present the detected badges. Auto-detected badges should be listed first with "(Recommended)" in their label. Include these additional optional badges the user can opt into:

Read the full file on GitHub · 133 lines

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. 2d ago First seen · 133 lines · 11 tokens per session scan A e73a8e91708d

Subscribe to this mod's changes

update-badges is a command published in the GitHub repository reggiechan74/cc-plugins (6 stars, last pushed 3mo ago), licensed MIT. It adds 11 tokens to every session and 1,367 once invoked, about $0.0001 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.