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 bendrucker/claude --skill modernizegit clone --depth 1 https://github.com/bendrucker/claudeWrote 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/bendrucker/claude/modernize)<a href="https://agentmods.dev/skills/bendrucker/claude/modernize"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/modernize.svg" alt="Measured on agentmods" 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 | $0.00071 | $0.01306 |
| Opus 5 | $0.00036 | $0.00653 |
| Sonnet 5 | $0.00014 | $0.00261 |
| Haiku 4.5 | $0.00007 | $0.00131 |
Grade A, and why
modernize scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **Detect the real runtime before assuming a language floor.** A Bun or Deno project has no `engines.node`. Bun implements `node:fs`, `child_process`, and friends, so swapping them for `Bun.file`/`Bun.$` is lateral chur How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Modernize
Find where a project still does things the old way because newer features did not exist when it was written, and propose semantics-preserving swaps. The deliverable is a ranked survey of candidates the user picks from. Applying is a separate phase, run only on the candidates they choose.
Language-agnostic by design. Detect the stack, never assume it.
Modernization axes
Two axes, plus a third that is easy to miss:
- Language features. Syntax and stdlib additions that replace boilerplate: pattern matching, comprehensions,
async/awaitover callbacks, records and dataclasses, native nullability, structured concurrency. - Major dependencies. Framework and major-library APIs that supersede older usage, such as a new router, data-fetching primitive, or config format. Frameworks and load-bearing libraries only, not every transitive dependency.
- Stdlib subsumption. A third-party dependency the language or runtime has since absorbed, like native
fetch,structuredClone,Array.prototype.flat, orstd::format. Retiring a now-redundant dependency is the highest-leverage move, because it deletes code and a dependency at once.
Three disciplines
These separate modernization from churn. Hold them throughout.
-
Semantics-preserving. A modernization changes how the code is written, never what it does. Behavior, public API, and error modes stay identical. A swap that would change behavior is a feature change, and belongs in the report only as a flagged note.
-
Earn its keep. Newer is not a reason. Every candidate must buy something concrete: less boilerplate, stronger types or safety, a dropped dependency, real performance, or genuine clarity. Pure novelty is rejected. Churn has a cost (review burden, blame noise, risk) and the benefit must clear it.
-
Respect the floor. A project has a minimum supported version: the oldest runtime or language version it promises to run on (an app's deploy target, a library's declared
engines, edition, or*_requires). A feature newer than the floor cannot be adopted for free. Adopting it silently raises the floor and breaks consumers. Those candidates are flagged bumps, reported separately with the version they require, never applied as part of adopt-now. See references/survey.md.
What ships with it
4 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.
- 3d ago First seen · 64 lines · 71 tokens per session scan A d4f2dfe67a59
modernize is a skill published in the GitHub repository bendrucker/claude (16 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 1,306 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
phx-review
Review changed Elixir/Phoenix code read-only. Check requirements, cite evidence, deduplicate findings, and return a severity-based verdict.
plugin-dev
Validate plugin SKILL.md frontmatter and audit hook scripts for silent failures. Run validation to check all plugins pass schema, source path, and frontmatter checks. Run hook audit to detect unhandled errors in shell and Python scripts.
content-audit
Content file quality audit across 8 dimensions (CC1-CC8): encoding artifacts (NBSP, mojibake, zero-width), markdown syntax (broken italic, orphan backslash), CMS migration artifacts (Joomla/WordPress/PHP), frontmatter quality, image integrity, link integrity with anchor validation, content completeness, and…
fec-refactor-clean
A safe cleanup workflow for unused front-end code, exports, routes, components, and dependencies.
fec-legacy-web-standard
A maintenance guide for older web projects built with plain JavaScript, jQuery, HTML, CSS, or server-rendered templates.
project-setup
Setup and hardening review for cross-platform modern-C++ (C++17) native projects, especially Node.js addons built with node-gyp / node-addon-api. Use when asked to "set up a native addon", "harden a C/C++ build", "review my binding.gyp", "add compiler hardening flags", "wire up AddressSanitizer/UBSan/TSan/clang-tidy"…