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.
npx skills add ikotelkin/claude-skills --skill frugal-subagentsgit 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/skills/ikotelkin/claude-skills/frugal-subagents)<a href="https://agentmods.dev/skills/ikotelkin/claude-skills/frugal-subagents"><img src="https://agentmods.dev/badge/skills/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/skills/ikotelkin/claude-skills/frugal-subagents"><img src="https://agentmods.dev/badge/skills/ikotelkin/claude-skills/frugal-subagents.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 | $0.00211 | $0.02074 |
| Opus 5.5 | $0.00084 | $0.00830 |
| Sonnet 5.5 | $0.00042 | $0.00415 |
| Haiku 4.5 | $0.00021 | $0.00207 |
Grade B, and why
frugal-subagents scanned grade B with 2 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 1mo 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
2. Offer to install Node.js LTS and wait for a yes. Use the platform's package manager: Windows `winget install OpenJS.NodeJS.LTS`; macOS `brew install node` (or the installer from nodejs.org if Homebrew is absent); Debi Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
const {spawnSync}=require('child_process'); How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frugal Subagents
Why
Delegation is where a session's budget leaks. Subagents inherit the parent's model unless told otherwise, so a top-tier session that fans out three research agents is running three more copies of its most expensive model — and if one of them fans out again, the cost multiplies silently. On subscription plans that can exhaust the limit in minutes, with most results lost to rate limits. Written rules ("use sonnet for scans") don't survive context compaction; this plugin turns them into a hook, which does.
What the hook enforces
Every Agent call passes through hooks/guard.js before it runs. Nothing is silent: when the hook fills in a model it says so in the tool result, and a blocked call returns the reason as tool feedback.
| Rule | Default | Lift / tune |
|---|---|---|
No model given → the default cheap model is injected |
sonnet |
FRUGAL_SUBAGENTS_DEFAULT_MODEL=haiku; strict mode FRUGAL_SUBAGENTS_REQUIRE_MODEL=1 denies instead of defaulting |
| No subagents from inside a subagent | on | FRUGAL_SUBAGENTS_ALLOW_NESTED=1 |
| Spawns per session | 12 | FRUGAL_SUBAGENTS_MAX_SPAWNS=<n> |
| Ceiling on subagent tier | off | FRUGAL_SUBAGENTS_MAX_TIER=sonnet (or haiku, opus) |
| Everything off | — | FRUGAL_SUBAGENTS_OFF=1 |
Variables go into the user's or project's settings.json under "env", or the shell environment. The user changes them, not the session: a denied call is policy, and splitting or rephrasing a call to get around it is not an option.
How to delegate under the guard
Pick the tier by what the work costs, not by how important it feels. Search/fetch volume, page scanning, listing comparison, extraction, renames, tests-to-a-spec → sonnet or haiku (leaving model out gives the default, sonnet). The session's own top-tier model is for judgment that cannot be delegated — decomposition, contested decisions, final synthesis — and normally stays in the main session; name it explicitly on a subagent only when that judgment genuinely has to run in a separate context.
What ships with it
6 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.
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.
- 1mo ago First seen · 96 lines · 211 tokens per session scan B 23889c313104
frugal-subagents is a skill published in the GitHub repository ikotelkin/claude-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 211 tokens to every session and 2,074 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-08.
Other skills, from other repositories
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
design-review
Review a web app or page for visual design quality — layout, typography, spacing, colour, hierarchy, consistency, interaction patterns, and responsive behaviour. Not a UX audit (that checks usability) — this checks whether it looks professional and polished. Produces a design findings report with screenshots.…
react-patterns
React 19 performance patterns and composition architecture for Vite + Cloudflare projects. 50+ rules ranked by impact — eliminating waterfalls, bundle optimisation, re-render prevention, composition over boolean props, server/client boundaries, and React 19 APIs. Use when writing, reviewing, or refactoring React…
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the chosen backdrop colour, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed…
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…