bundle-skills

bundle-skills is a skill for Claude Code from 5kahoisaac/skillless. It costs 129 tokens per session (1,855 once invoked), scanned A, original, MIT.

A workflow for creating or updating CSV bundles of skills for the skillless project. Each bundle is a category file listing repositories, skill names, and supported agents.

In plain words
What is it for?
Use it to plan, merge, sort, and verify skill bundles before installing them.
Why use it?
It turns a broad request such as a Python or frontend bundle into a sorted, reviewable list that the skillless CLI can use.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Codex; mentions OpenCode.

Good fit Use it to plan, merge, sort, and verify skill bundles before installing them.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/5kahoisaac/skillless/bundle-skills
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 5kahoisaac/skillless --skill bundle-skills
Clone the repo
git clone --depth 1 https://github.com/5kahoisaac/skillless

Made for: Claude Code.

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 bundle-skills

README.md
[![agentmods](https://agentmods.dev/badge/skills/5kahoisaac/skillless/bundle-skills/github.svg)](https://agentmods.dev/skills/5kahoisaac/skillless/bundle-skills)
Your own site
<a href="https://agentmods.dev/skills/5kahoisaac/skillless/bundle-skills"><img src="https://agentmods.dev/badge/skills/5kahoisaac/skillless/bundle-skills/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.

agentmods 80×15 button for bundle-skills

Your own site · 80×15
<a href="https://agentmods.dev/skills/5kahoisaac/skillless/bundle-skills"><img src="https://agentmods.dev/badge/skills/5kahoisaac/skillless/bundle-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,855 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 $0.00129 $0.01855
Opus 5 $0.00064 $0.00928
Sonnet 5 $0.00026 $0.00371
Haiku 4.5 $0.00013 $0.00186

Measured 9d ago against content hash 41bb719c5405, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

bundle-skills 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 9d 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/skills/bundle-skills/SKILL.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bundle Skills

This project stores skill bundles as CSV files under lists/. A bundle is a category file consumed by the skillless CLI.

Use this workflow to help a user turn a loose request like /bundle-skills frontend into a reviewed, safe, sorted CSV bundle.

Repository conventions

  • Bundle files live in lists/<category>.csv.
  • CSV header is always:
    repo,skill_name,agents
    
  • repo is a GitHub owner/repo or supported URL.
  • skill_name is the skill to install. Empty means “install all skills from that repo”; use this only when intentionally bundling the whole repo.
  • agents is space-separated, commonly opencode claude-code codex.
  • Sort final CSV rows by repo alphabetically, then by skill_name for stable diffs.
  • Verify the bundle with ./skillless list and, when safe, ./skillless -n pack <category>.

Workflow

1. Interpret the user’s bundle idea

Extract the raw requested domain from the prompt.

Examples:

  • /bundle-skills frontend → broad frontend bundle.
  • /bundle-skills react testing → React-focused testing bundle.
  • /bundle-skills backend node → Node/backend bundle.

Rewrite the idea into a generic intent and split it into subgroups. For broad topics, do not treat the first word as a single bucket.

Example split for frontend:

  • Core frontend engineering
  • Frameworks such as React, Next.js, Vue, Angular, Svelte
  • Styling and CSS systems such as Tailwind, design systems, animation
  • Testing and browser automation
  • Accessibility, UX, and performance

Keep the split practical. The goal is a useful bundle, not exhaustive taxonomy.

2. Confirm scope before searching deeply

Ask the user to confirm the interpreted idea and fill missing decisions that affect the search.

Ask only what matters. Typical questions:

  • Bundle name: should this become lists/<name>.csv?
  • Framework focus: generic, React/Next.js, Vue, Angular, backend-specific, etc.?
  • Target agents: default to opencode claude-code codex unless the user wants fewer.
  • Merge policy: if a related CSV already exists, should the final result merge into it or create a new bundle?

Read the full file on GitHub · 234 lines

Files

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.

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. 9d ago First seen · 234 lines · 129 tokens per session scan A 41bb719c5405

Subscribe to this mod's changes

bundle-skills is a skill published in the GitHub repository 5kahoisaac/skillless (4 stars, last pushed 1mo ago), licensed MIT. It adds 129 tokens to every session and 1,855 once invoked, about $0.0006 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.