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 xiaohei-info/oh-my-multica --skill software-development-normsgit clone --depth 1 https://github.com/xiaohei-info/oh-my-multicaWrote 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/xiaohei-info/oh-my-multica/software-development-norms)<a href="https://agentmods.dev/skills/xiaohei-info/oh-my-multica/software-development-norms"><img src="https://agentmods.dev/badge/skills/xiaohei-info/oh-my-multica/software-development-norms/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/xiaohei-info/oh-my-multica/software-development-norms"><img src="https://agentmods.dev/badge/skills/xiaohei-info/oh-my-multica/software-development-norms.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00066 | $0.06723 |
| Opus 5.5 | $0.00026 | $0.02689 |
| Sonnet 5.5 | $0.00013 | $0.01345 |
| Haiku 4.5 | $0.00007 | $0.00672 |
Grade A, and why
software-development-norms 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 1mo 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 — 839 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Software Development Norms
Industrial-grade software engineering rules abstracted from the Alibaba Java Development Handbook (Huangshan Edition). Every principle is language-agnostic; each rule uses a single illustrative example instead of cross-language comparison.
Overview
The Alibaba Java Development Handbook is a benchmark for enterprise-grade coding standards in China. Its rules are rooted in engineering wisdom — not language-specific syntax. This skill distills those rules into universal principles and warns against common anti-patterns that appear across codebases.
When you write code in any language, load this skill to check your work against battle-tested norms.
When to Use
- Writing new code in any language and want to follow professional conventions
- Reviewing code for quality, readability, and robustness
- Onboarding onto a project and need to internalize its baseline quality bar
- Refactoring code and want to avoid introducing anti-patterns
- Deciding on naming, error handling, concurrency, or project structure conventions
Do NOT use for:
- Language-specific style guide enforcement (use language linters instead)
- Debating syntax preferences that have no engineering impact
1. Naming
1.1 No abbreviations that obscure meaning
Principle: Names must be self-documenting. Never abbreviate by dropping letters arbitrarily — the reader must understand the intent without guessing.
# Good
remaining_retry_count = 3
pull_code_from_remote_repository()
# Bad
rmng_rtry_cnt = 3
a = 3
Anti-pattern: AbsClass for AbstractClass, condi for condition. If you can't say it out loud without explaining the abbreviation, the name is wrong.
1.2 Consistent naming conventions per scope
Principle: Each scope (package/module, class/struct, method/function, constant, variable) follows a single convention within the project. Mixed conventions create cognitive load.
Project rule: Define one naming convention per scope and apply it consistently across the repository.
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.
- 1mo ago First seen · 839 lines · 66 tokens per session scan A 671b90447caf
software-development-norms is a skill published in the GitHub repository xiaohei-info/oh-my-multica (37 stars, last pushed 17d ago), licensed MIT. It adds 66 tokens to every session and 6,723 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
review
Diff-scoped correctness review that reads the codebase around the change — callers, contracts, and invariants — and returns line-anchored findings ranked by severity with confidence, then a merge-risk verdict. Use for reviewing a PR, diff, or named change set. Not for style review, approvals-as-rubber-stamp, or…
cw-slice
Use before writing code for any Codewhale feature, upgrade, or refactor: find the existing owner of the behavior, bound the change to one reviewable slice, and fix the evidence bar before you start.
simplify
Improve clarity and reduce needless complexity after behavior is understood; preserve behavior and keep cleanup separate from correctness fixes.
doubt-driven-review
In-flight adversarial check on a non-trivial decision BEFORE it stands — distinct from post-hoc review of a finished diff. Use on "stress-test this decision", "are we sure about this", "verify before commit", "poke holes in this", when working in unfamiliar code, or before an irreversible step (migration, prod deploy…