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 brackendev/clojurescript-skills --skill clojurescript-lensesgit clone --depth 1 https://github.com/brackendev/clojurescript-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/brackendev/clojurescript-skills/clojurescript-lenses)<a href="https://agentmods.dev/skills/brackendev/clojurescript-skills/clojurescript-lenses"><img src="https://agentmods.dev/badge/skills/brackendev/clojurescript-skills/clojurescript-lenses/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/brackendev/clojurescript-skills/clojurescript-lenses"><img src="https://agentmods.dev/badge/skills/brackendev/clojurescript-skills/clojurescript-lenses.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 | $0.00160 | $0.02862 |
| Opus 5.5 | $0.00064 | $0.01145 |
| Sonnet 5.5 | $0.00032 | $0.00572 |
| Haiku 4.5 | $0.00016 | $0.00286 |
Grade A, and why
clojurescript-lenses 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 2d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Lenses for ClojureScript
Layered on top of clojure-lenses (in clojure-skills), which covers the host-neutral Clojure translations. This skill records only the ClojureScript-specific deltas that the baseline does not address: JavaScript interop boundaries, externs and advanced compilation, macro stage separation, the JS event loop, the absence of refs / agents / STM, and the limits of var reification.
The default code-lenses review set is grug, honest-code, tidy-first, and parse-dont-validate. aposd and legacy-code are opt-in (added with +aposd or +legacy-code, or invoked directly). The sections below apply when the corresponding lens is active; APOSD and Legacy Code translations are present so the lens can use them when explicitly invoked, but they are not part of the default trigger set.
When the code-lenses plugin is active in a ClojureScript project, apply the baseline clojure-lenses translations first; reach for this skill for the JavaScript-specific additions below.
Grug Brain
- Default building blocks remain maps, vectors, and sets with namespaced keys. JavaScript objects belong at the interop boundary only; convert with
clj->jsandjs->cljonce and operate on Clojure data inside the namespace. - Reach for
deftypeonly when implementing a JavaScript protocol or interop that requires a named prototype. Use plain functions and data for everything else. - The macro / function divide is its own complexity: macros must live in
.cljor.cljcfiles and be required via:require-macros,:refer-macros, or:include-macros. Treat that as a reason to prefer functions; reach for macros only when the macro is doing real syntactic work that a function cannot. - REPL-driven development on ClojureScript means the browser REPL or Node REPL. Spike in the REPL before introducing abstractions. The cost of starting a CLJS REPL is higher than a JVM REPL, so once a REPL is up, keep using it.
:advancedcompilation is a complexity demon waiting to happen. Enable externs inference (:infer-externs true,*warn-on-infer*) early and add^js/^js/Foo.Barhints incrementally so production builds do not surprise you.- Reagent / re-frame / Fulcro are powerful, but they are abstraction. A vector of hiccup and an atom is simpler when the problem fits. Reach for a framework when the open polymorphism it provides matches a real need.
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.
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.
- 2d ago Changed 318b0e5972ba
- 4d ago Changed · -1 lines acae729cd76c
- 23d ago Changed f8335809cf6e
- 1mo ago First seen · 89 lines · 160 tokens per session scan A 82b1f48fea67
clojurescript-lenses is a skill published in the GitHub repository brackendev/clojurescript-skills (1 stars, last pushed 2d ago), licensed MIT. It adds 160 tokens to every session and 2,862 once invoked, about $0.0006 per session on Opus 5.5. 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
phx-review
Review changed Elixir/Phoenix code read-only. Check requirements, cite evidence, deduplicate findings, and return a severity-based verdict.
r-tidyverse-style
Use when the user asks to review or clean up R code for tidyverse style, standardize formatting or names, remove redundant comments or wrappers, or make a behavior-preserving style pass. Also use when writing substantial new R package code if the user requests tidyverse style or the package already follows it. Not for…
python-services
Python patterns for CLI tools, async parallelism, and backend services. Use when building CLI apps, async/parallel Python, FastAPI services, background jobs, or configuring Python project tooling (uv, ruff, ty).
react-frontend
React, TypeScript, and Next.js patterns for frontend development. Use when building React components, managing state, fetching data, optimizing performance, or working with Next.js App Router. Covers React 18-19, hooks, Server Components, and type-safe patterns.
pinescript
Pine Script v6 patterns: syntax rules, performance, debugging, backtesting, visualization. Use when asked to "write a Pine Script", "create an indicator", "build a strategy", "fix Pine code", or mentions PineScript, TradingView, indicator, strategy, or backtest.
clojure-expert
Expert knowledge in Clojure/ClojureScript, immutability, REPL-driven development, core.async, and functional programming on the JVM. Use when the user mentions ClojureScript, functional programming, immutability, REPL, core async, or JVM, or when the task involves Lisp Features, Concurrency, REPL-Driven Development…