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 mickeyyaya/refactoring-skills --skill cross-language-review-heuristicsgit clone --depth 1 https://github.com/mickeyyaya/refactoring-skillsWrote 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/mickeyyaya/refactoring-skills/cross-language-review-heuristics)<a href="https://agentmods.dev/skills/mickeyyaya/refactoring-skills/cross-language-review-heuristics"><img src="https://agentmods.dev/badge/skills/mickeyyaya/refactoring-skills/cross-language-review-heuristics/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/mickeyyaya/refactoring-skills/cross-language-review-heuristics"><img src="https://agentmods.dev/badge/skills/mickeyyaya/refactoring-skills/cross-language-review-heuristics.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00095 | $0.02723 |
| Opus 5 | $0.00048 | $0.01362 |
| Sonnet 5 | $0.00019 | $0.00545 |
| Haiku 4.5 | $0.00010 | $0.00272 |
Grade A, and why
cross-language-review-heuristics 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 12d 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-Language Review Heuristics
Overview
Some code review signals transcend language syntax. The same structural problems produce the same categories of bugs, maintenance burden, and security risk across all languages.
Universal heuristics are distinct from language-specific idioms. This skill teaches what is structurally problematic in any ecosystem — use it as the first pass, then load the language-specific skill for fine-grained calibration.
Naming Clarity
Clear naming is the lowest-cost form of documentation.
Thresholds
Single-character variables acceptable only in tight loops (i, j, k; n for count; x, y for coordinates). Flag at LOW otherwise.
Abbreviations require a project glossary or are limited to universal ones (id, url, err, ctx, msg). Flag inconsistent or undocumented abbreviations at LOW.
Boolean naming must use an assertion prefix: is, has, should, can, was, needs. Flag ambiguous booleans (active, loading) at LOW.
Function naming must follow a verb-noun structure. Flag vague or noun-only names (data(), handler(), process()) at LOW. Flag single-word functions with side effects at MEDIUM if the name implies purity.
Language-Specific Calibration
- Go: exported identifiers must be fully spelled out; unexported identifiers in short functions may use short names if scope is less than 10 lines
- Python: snake_case for variables/functions; PascalCase for classes; SCREAMING_SNAKE_CASE for constants
- TypeScript/JavaScript: camelCase for variables and functions; PascalCase for classes and React components; ALL_CAPS for module-level constants
- Rust: snake_case for functions and variables; PascalCase for types and traits; SCREAMING_SNAKE_CASE for constants
- Java: camelCase for methods and variables; PascalCase for classes; ALL_CAPS for constants in interfaces
Complexity Thresholds
Cyclomatic complexity correlates linearly with bug count.
Cyclomatic Complexity
Each if, else if, for, while, case, catch, &&, and || adds 1.
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.
- 12d ago First seen · 232 lines · 95 tokens per session scan A d300936d3fe3
cross-language-review-heuristics is a skill published in the GitHub repository mickeyyaya/refactoring-skills (6 stars, last pushed 5mo ago), licensed MIT. It adds 95 tokens to every session and 2,723 once invoked, about $0.0005 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…