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 agentmods add skills/adambien/airails/zjsonnpx skills add AdamBien/airails --skill zjsongit clone --depth 1 https://github.com/AdamBien/airailsWrote 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/adambien/airails/zjson)<a href="https://agentmods.dev/skills/adambien/airails/zjson"><img src="https://agentmods.dev/badge/skills/adambien/airails/zjson.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 | $0.00109 | $0.01492 |
| Opus 5 | $0.00055 | $0.00746 |
| Sonnet 5 | $0.00022 | $0.00298 |
| Haiku 4.5 | $0.00011 | $0.00149 |
Grade A, and why
zjson 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Copy the three files from GitHub, preserving the `org/json` path. This is the canonical method — it needs only `curl` and works on any machine, with no local checkout or extra tooling: How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
zjson — JSON via Source Copy
Add JSON parsing and generation to a Java project by copying the org.json source files in — no Maven or Gradle dependency.
What is zjson
A Java 25, zero-dependency fork of the org.json reference implementation, trimmed to three classes:
-
JSONObject— JSON object: key/value map with typed accessors -
JSONArray— JSON array: ordered values,Iterable<Object> -
JSONTokener— the parser both classes delegate to -
Package:
org.json -
Source: https://github.com/AdamBien/z-JSON-java (
src/main/java/org/json) -
Requires: Java 21+ (developed against Java 25)
Not included in this fork: JSONStringer, JSONWriter, XML/CDL/HTTP/Cookie conversion. Use JSONObject and JSONArray for building output.
Source Integration
Copy the org/json package into the project's source root — keep the package org.json; declarations unchanged. Unlike single-class utilities, the package is not repackaged; org.json stays as-is and is imported with import org.json.*;.
Copy the three files from GitHub, preserving the org/json path. This is the canonical method — it needs only curl and works on any machine, with no local checkout or extra tooling:
for f in JSONObject JSONArray JSONTokener; do
curl -sf "https://raw.githubusercontent.com/AdamBien/z-JSON-java/main/src/main/java/org/json/$f.java" \
-o "src/main/java/org/json/$f.java" --create-dirs
done
For a single-file zb/CLI project whose source root is the project root, drop the src/main/java/ prefix and copy into org/json/ directly. After copying, build normally (e.g. /zb). The three files compile alongside application code with no further configuration.
Optional local shortcut: if a z-JSON-java checkout and the zjsoncp script are present on the machine, running zjsoncp from the source root copies the same org/json package locally. This is a convenience only — the curl method above is the portable default.
API
Parsing
import org.json.*;
JSONObject obj = new JSONObject("""
{"name":"Duke","age":29,"tags":["java","jvm"],"active":true}
""");
String name = obj.getString("name"); // "Duke"
int age = obj.getInt("age"); // 29
boolean active = obj.getBoolean("active"); // true
JSONArray tags = obj.getJSONArray("tags"); // ["java","jvm"]
JSONArray arr = new JSONArray("[1,2,3]");
int first = arr.getInt(0); // 1
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.
- 5d ago First seen · 127 lines · 109 tokens per session scan A 7276ce551d1a
zjson is a skill published in the GitHub repository AdamBien/airails (48 stars, last pushed 15d ago), licensed MIT. It adds 109 tokens to every session and 1,492 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
java-coding-standards
Java coding standards for Spring Boot services: naming, immutability, Optional usage, streams, exceptions, generics, and project layout.
java-boilerplate
Gera automaticamente getters, setters, construtores, toString, equals e hashCode para classes Java. Triggers on: /java-boilerplate, 'gerar métodos java', 'criar getters setters'.
springboot-patterns
Spring Boot architecture patterns, REST API design, layered services, data access, caching, async processing, and logging. Use for Java Spring Boot backend work.
remove-deprecated-api
AEM Cloud Service expert skill — migrate deprecated and removed Java APIs to comply with AEM as a Cloud Service enforcement policies. Detection is plugin-driven, not table-driven: the skill runs the AEM Analyser Maven Plugin (com.adobe.aem:aemanalyser-maven-plugin) at its latest published version against the project…
outdated-dependencies
AEM Cloud Service expert skill — upgrade outdated Maven dependencies in pom.xml, both literal and same-pom ${property} shapes. Use for "update my aem-sdk-api", "upgrade mockito", or scanning a project for stale dependency versions. Discovery can find blocks but "outdated" needs a target version, which the user…
inject-in-sling-model
AEM Cloud Service expert skill — migrate javax.inject.@Inject fields in Sling Model (@Model) classes to injector-specific annotations (@ValueMapValue / @OSGiService / @SlingObject). Self-discoverable (scan for @Model classes with field-level @Inject); the replacement is chosen deterministically from each field's…