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.
git clone --depth 1 https://github.com/ikotelkin/claude-skillsWrote 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/plugins/ikotelkin/claude-skills/frugal-subagents)<a href="https://agentmods.dev/plugins/ikotelkin/claude-skills/frugal-subagents"><img src="https://agentmods.dev/badge/plugins/ikotelkin/claude-skills/frugal-subagents/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/plugins/ikotelkin/claude-skills/frugal-subagents"><img src="https://agentmods.dev/badge/plugins/ikotelkin/claude-skills/frugal-subagents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
frugal-subagents 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 4d 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.
What it actually says
{
"name": "frugal-subagents",
"displayName": "Frugal Subagents",
"version": "1.0.0",
"description": "On Claude Fable 5.1 (or Opus), Claude's helpers (subagents) inherit your expensive model and can start helpers of their own — one web research pass can burn a session's usage limit in minutes, and an instruction to be frugal doesn't survive context compaction. frugal-subagents builds the limits in: helpers run on a cheaper model (Sonnet by default) unless Claude asks for a stronger one, helpers can't start helpers, at most 12 per session — enforced by a PreToolUse hook — plus two ready-made cheap helpers for web research and extraction that save findings to files and return short summaries.",
"author": {
"name": "Ivan Kotelkin",
"url": "https://github.com/ikotelkin"
},
"homepage": "https://github.com/ikotelkin/claude-skills",
"repository": "https://github.com/ikotelkin/claude-skills",
"license": "MIT",
"keywords": [
"subagents",
"tokens",
"budget",
"usage-limit",
"fable-5.1",
"claude-fable",
"opus",
"sonnet",
"hooks",
"model-routing",
"guardrails"
],
"skills": [
"."
]
}
What it installs
The manifest is a name and a version. 1 skill, 2 agents, 1 hook travel with it, and installing the plugin installs all of them — 328 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 4d ago First seen · 30 lines scan A 03b7352d21c4
frugal-subagents is a plugin published in the GitHub repository ikotelkin/claude-skills (3 stars, last pushed 5d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-08.
Other plugins, from other repositories
i-have-adhd
Shape Claude Code output for an ADHD reader: lead with the next action, number steps, suppress tangents, restate state, make wins visible.
visual-documentation-plugin
Skills for creating stunning visual HTML documentation with modern UI design, SVG diagrams, flowcharts, dashboards, timelines, technical documentation, and comprehensive project architecture diagrams.
code-operations-plugin
Skills for code manipulation operations including line-based code transfer, bulk refactoring, and file analysis - converted from code-copy-mcp.
slideops
Turn a repository into a slide deck or Markdown docs, then find out the day they stop matching the code. Ships slideops (repo to deck or cited Markdown doc, with citation-based freshness checking) and slides-to-pdf (any hash-navigated HTML deck to a verified PDF).
lore
Persistent project knowledge base for Claude Code. Records current state, phased roadmap, decisions and their rejected alternatives, and failed approaches — so a new session resumes from what was recorded instead of re-reading the whole codebase.
senior-dev-skills marketplace
Plugin marketplace listing 1 plugin: senior-dev-skills.