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/openhands/extensions/build-setupnpx skills add OpenHands/extensions --skill build-setupgit clone --depth 1 https://github.com/OpenHands/extensionsWhat 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 | $0.00031 | $0.00612 |
| Opus 5 | $0.00015 | $0.00306 |
| Sonnet 5 | $0.00006 | $0.00122 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
build-setup 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up a build environment and create test fixtures for validating COBOL-to-Java migrations.
To install GnuCOBOL, run: ./scripts/install-gnucobol.sh
On Windows, run that shell script from Git Bash/WSL (bash scripts/install-gnucobol.sh) or install GnuCOBOL with a Windows package manager and document the chosen command in build_notes.md.
Phase 1: Build Setup
COBOL Build
- Find a way to compile and run the COBOL code (e.g., GnuCOBOL)
- Verify at least one program compiles and executes
- Note any dependencies or setup required
Java Build
- Initialize a Java project alongside the COBOL code (Maven or Gradle)
- Set up standard directory structure:
src/main/java,src/test/java - Include JUnit 5 as a test dependency
- Verify the project builds (even if empty)
Phase 2: Test Fixture Generation
For each major COBOL program:
Create Synthetic Test Inputs
- Save to:
test-fixtures/inputs/{PROGRAM_NAME}/ - Create 3-5 test cases per program covering:
- Normal/happy path (valid, typical data)
- Edge cases (empty input, maximum values, boundary conditions)
- Error cases (invalid formats, missing required fields)
Generate Golden Outputs
- Run each COBOL program with each test input
- Save COBOL output to:
test-fixtures/expected_outputs/{PROGRAM_NAME}/ - These become the "golden" outputs that Java must match
Create Test Manifest
Save to test_manifest.json:
{
"PROGRAM1": {
"description": "Brief description of what this program does",
"test_cases": [
{
"name": "normal_invoice",
"input": "inputs/PROGRAM1/test_001.dat",
"expected": "expected_outputs/PROGRAM1/test_001.out",
"description": "Happy path"
}
]
}
}
Deliverables
- build_notes.md — Build instructions for COBOL and Java
- test-fixtures/ — Directory with
inputs/andexpected_outputs/ - test_manifest.json — JSON manifest of all test cases
Priority
Focus on programs with core business logic (transactions, calculations, data processing). UI-heavy programs (menu screens, reports) are lower priority.
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 First seen · 80 lines · 31 tokens per session scan A 922b0812ba60
build-setup is a skill published in the GitHub repository OpenHands/extensions (137 stars, last pushed 4d ago), licensed MIT. It adds 31 tokens to every session and 612 once invoked, about $0.0002 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 2026-08-30.
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…