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 tonyghiani/ai-essentials --skill dep-sizegit clone --depth 1 https://github.com/tonyghiani/ai-essentialsWrote 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/tonyghiani/ai-essentials/dep-size)<a href="https://agentmods.dev/skills/tonyghiani/ai-essentials/dep-size"><img src="https://agentmods.dev/badge/skills/tonyghiani/ai-essentials/dep-size/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/tonyghiani/ai-essentials/dep-size"><img src="https://agentmods.dev/badge/skills/tonyghiani/ai-essentials/dep-size.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 | $0.00060 | $0.00870 |
| Opus 5 | $0.00030 | $0.00435 |
| Sonnet 5 | $0.00012 | $0.00174 |
| Haiku 4.5 | $0.00006 | $0.00087 |
Grade A, and why
dep-size 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependency and bundle cost
Two jobs: decide whether a new dependency earns its place, and find the ones that already didn't.
Before adding a dependency
Answer these in order, and stop at the first that disqualifies it.
1. Does the platform already do this? Intl for dates, numbers, and currency. URL and URLSearchParams. structuredClone. Array.prototype.at/flat/group. crypto.randomUUID. AbortController. Most date formatting and deep-clone packages are now redundant.
2. Does the repo already have something? Grep package.json and the shared packages before reaching outside. Adding a second HTTP client, date library, or validation library is worse than using the awkward existing one.
3. What does it actually cost?
npx --yes bundlephobia@latest <pkg> # or check bundlephobia.com
npm view <pkg> dependencies
Report minified plus gzipped size, transitive dependency count, and whether it's tree-shakeable (ESM with sideEffects: false) or all-or-nothing.
4. Is it maintained and safe? Last publish date, open issue count, whether it's a single-maintainer package, and npm audit on it. A 2KB abandoned package with a prototype-pollution CVE is worse than 20KB that's maintained.
5. Is the alternative genuinely a lot of code? If the package replaces 15 lines you could write and test, write the 15 lines. If it replaces a date-parsing state machine, take the package.
Give a verdict: take it, write it inline, use what's already here, or take it but only on the server.
Finding existing bloat
Import shape. The most common and most fixable problem.
import _ from 'lodash'; // pulls the world
import { debounce } from 'lodash'; // better
import debounce from 'lodash/debounce'; // best where the build needs it
Grep for default imports of large libraries, import * as, and barrel imports that reach a whole package to use one symbol.
Server-only code in a browser bundle. A fs, path, or Node-only package imported from a file that ships to the client. In a plugin architecture, check that common/ doesn't pull server dependencies and that public/ entry points don't transitively import server modules.
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.
- 9d ago First seen · 71 lines · 60 tokens per session scan A ff395bd37c51
dep-size is a skill published in the GitHub repository tonyghiani/ai-essentials (6 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 870 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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…