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/score-stylenpx skills add OpenHands/extensions --skill score-stylegit 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 | $0.00022 | $0.00669 |
| Opus 5 | $0.00011 | $0.00334 |
| Sonnet 5 | $0.00004 | $0.00134 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
score-style 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluate migrated code against style guidelines and best practices.
This skill scores code quality aspects that are independent of functional correctness — focusing on readability, maintainability, and adherence to conventions.
Default Scoring Criteria
Unless a custom rubric is provided, score on these attributes (1-5 scale):
Naming Conventions (1-5)
- 1: Inconsistent or meaningless names
- 3: Mostly follows conventions, some issues
- 5: Clear, consistent, idiomatic names
Code Organization (1-5)
- 1: Monolithic, hard to navigate
- 3: Some structure, could be cleaner
- 5: Well-organized, logical structure
Error Handling (1-5)
- 1: Missing or swallowed exceptions
- 3: Basic error handling present
- 5: Comprehensive, appropriate error handling
Documentation (1-5)
- 1: No documentation
- 3: Some documentation, inconsistent
- 5: Thorough, helpful documentation
Idiomaticity (1-5)
- 1: Non-idiomatic, smells like translated code
- 3: Mostly idiomatic, some foreign patterns
- 5: Fully idiomatic, natural code
Output Format
Save scores as a JSON file:
{
"target_file_a.java": {
"naming_conventions": 4,
"code_organization": 3,
"error_handling": 5,
"documentation": 4,
"idiomaticity": 4,
"justification": "Good naming and error handling. Some methods could be extracted for better organization."
}
}
Custom Rubric
If a custom rubric is provided, use its attributes and scoring criteria instead of the defaults. The rubric should define:
- Attribute names
- Score meanings for each level (1-5)
- Examples of good/bad code for each attribute
Evaluation Guidelines
What to Look For
Positive indicators:
- Consistent naming (camelCase for Java, snake_case for Python)
- Appropriate class/method sizes
- Single responsibility principle followed
- Meaningful comments (not obvious ones)
- Standard library usage over custom implementations
- Defensive programming practices
Negative indicators:
- Literal translations (COBOL-style Java)
- God classes or methods
- Magic numbers
- Excessive comments or no comments
- Reinvented wheels
- Swallowed exceptions
- Hardcoded values
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 · 107 lines · 22 tokens per session scan A 7c461adc030d
score-style is a skill published in the GitHub repository OpenHands/extensions (137 stars, last pushed 4d ago), licensed MIT. It adds 22 tokens to every session and 669 once invoked, about $0.0001 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…