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/lftpadilla/agent-dev-kit/java-developmentnpx skills add LFTPadilla/agent-dev-kit --skill java-developmentgit clone --depth 1 https://github.com/LFTPadilla/agent-dev-kitWhat 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 | $0.00084 | $0.02393 |
| Opus 5 | $0.00042 | $0.01196 |
| Sonnet 5 | $0.00017 | $0.00479 |
| Haiku 4.5 | $0.00008 | $0.00239 |
Grade A, and why
java-development 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 yesterday.
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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Java development
Treat the repository as the source of truth. This skill is a workflow contract, not a request to convert a project to a preferred Java stack.
Non-negotiable contract
- Discover before executing. Read repository instructions, CI workflows,
wrapper files, build descriptors, settings, module declarations, toolchain or
release configuration, and existing test/quality plugins. Run
scripts/java-project-detect.sh <repo>for an advisory, read-only summary. - Use the project wrapper. Prefer
./mvnwor./gradlew; do not substitute a globally installed Maven or Gradle. If both build systems are present, resolve the intended build root from repository instructions and CI rather than guessing. Use a system tool only when no wrapper exists, the repository documents that path, and the command is available. - Honor the pinned JDK and target. Distinguish the JDK running the build or
language server, the toolchain compiling/testing the project, and the
bytecode/API target (
--release,maven.compiler.release, or equivalent). Do not change compatibility settings merely to make the local machine pass. - Diagnose before patching. Reproduce the exact compile/test failure, keep
the full first relevant exception and
Caused bychain, identify the failing module/task/phase, and separate environment/toolchain failures from product defects. Do not make speculative edits while a prerequisite is missing. - Use a tight evidence loop. For behavior changes, add or identify the focused test, observe the expected failure, implement the smallest change, rerun that test, then the affected module and configured project/CI gates.
- Preserve project policy. Do not disable tests or analyzers, add blanket suppressions, lower coverage thresholds, weaken dependency verification, or rewrite generated files to obtain a green build.
- Verify independently. Inspect the final diff and generated-file status, then report exact commands, exit results, skipped checks, and prerequisites. A worker summary, IDE diagnostic, Graphify edge, or green focused test alone is not completion evidence.
What ships with it
2 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.
- yesterday First seen · 213 lines · 84 tokens per session scan A 687bc67ac49b
java-development is a skill published in the GitHub repository LFTPadilla/agent-dev-kit (2 stars, last pushed 4d ago), licensed MIT. It adds 84 tokens to every session and 2,393 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…