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 FradSer/dotclaude --skill best-practicesgit clone --depth 1 https://github.com/FradSer/dotclaudeWrote 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/fradser/dotclaude/best-practices)<a href="https://agentmods.dev/skills/fradser/dotclaude/best-practices"><img src="https://agentmods.dev/badge/skills/fradser/dotclaude/best-practices/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/fradser/dotclaude/best-practices"><img src="https://agentmods.dev/badge/skills/fradser/dotclaude/best-practices.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 | $0.00052 | $0.00472 |
| Opus 5.5 | $0.00021 | $0.00189 |
| Sonnet 5.5 | $0.00010 | $0.00094 |
| Haiku 4.5 | $0.00005 | $0.00047 |
Grade A, and why
best-practices 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 22d 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.
What it actually says
Best Practices
Language References
Each file extension maps to a specific reference:
.ts,.js—references/typescript.md.tsx,.jsx—references/typescript.md+references/react/react.md.py—references/python.md+references/python/INDEX.md.go—references/go.md.swift—references/swift.md
Universal principles are in references/universal.md.
Next.js/React References
For Next.js projects, the references/react/ directory provides:
references/react/rules/INDEX.md— pattern index by impact levelreferences/react/rules/_sections.md— priorities and categories- Specific rule files matching observed patterns
Rule Application
- Framework-specific rules (e.g., Next.js) apply only when that framework is detected
- CRITICAL rules have highest priority: waterfalls, bundle size, hydration
- All refactoring MUST preserve behavior and public interfaces
Code Quality Standards
- Comments: Only for complex business logic; code-restating comments are unnecessary
- Error Handling: Try-catch only where recoverable; no defensive checks in trusted paths
- Type Safety: No
any; proper types orunknownwith guards are required - Style: Existing code style and CLAUDE.md conventions take precedence
- Cleanup: Unused imports, variables, functions, and types are removed
- No compat hacks: Unused
_varsand re-exports of deleted code are deleted - Renaming: Descriptive names are preferred over marking as unused
- Dead code: Dead code is deleted, never commented out
- File Organization: Single Responsibility applies at file level; files with multiple concerns are candidates for splitting (see
references/universal.md)
What ships with it
60 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.
- references/_template.md 631 B
- references/go.md 9.6 KB
- references/python.md 8.8 KB
- references/python/_sections.md 973 B
- references/python/_template.md 668 B
- references/python/fundamental-background.md 594 B
- references/python/fundamental-exceptions.md 2.0 KB
- references/python/fundamental-future-imports.md 1.3 KB
- references/python/fundamental-global-state.md 1.5 KB
- references/python/fundamental-imports.md 1.6 KB
- references/python/fundamental-packages.md 1.1 KB
- references/python/fundamental-resources.md 1.5 KB
- references/python/fundamental-threading.md 1.5 KB
- references/python/INDEX.md 5.6 KB
- references/python/language-comprehensions.md 1.1 KB
- references/python/language-conditionals.md 1.1 KB
- references/python/language-decorators.md 1.4 KB
- references/python/language-default-args.md 1.2 KB
- references/python/language-generators.md 1.6 KB
- references/python/language-getters-setters.md 1.1 KB
- references/python/language-iterators.md 939 B
- references/python/language-lambda.md 1.4 KB
- references/python/language-lexical-scoping.md 818 B
- references/python/language-nested-classes.md 544 B
- references/python/language-power-features.md 1.9 KB
- references/python/language-properties.md 836 B
- references/python/language-true-false.md 854 B
- references/python/quality-function-length.md 1.6 KB
- references/python/quality-lint.md 1.0 KB
- references/python/quality-main.md 993 B
- references/python/quality-todos.md 1.2 KB
- references/python/quality-type-annotated-code.md 1.2 KB
- references/python/quality-type-annotations.md 3.0 KB
- references/python/style-blank-lines.md 675 B
- references/python/style-comments.md 1.9 KB
- references/python/style-imports-formatting.md 1.2 KB
- references/python/style-indentation.md 1017 B
- references/python/style-line-length.md 994 B
- references/python/style-naming.md 1.9 KB
- references/python/style-parentheses.md 589 B
- references/python/style-parting-words.md 728 B
- references/python/style-semicolons.md 462 B
- references/python/style-shebang.md 409 B
- references/python/style-statements.md 657 B
- references/python/style-strings.md 1.3 KB
- references/python/style-whitespace.md 1.0 KB
- references/react/react.md 5.6 KB
- references/react/rules/_sections.md 1.5 KB
- references/react/rules/_template.md 631 B
- references/react/rules/advanced-event-handler-refs.md 1.4 KB
- references/react/rules/advanced-init-once.md 958 B
- references/react/rules/advanced-use-latest.md 1.0 KB
- references/react/rules/async-api-routes.md 1.1 KB
- references/react/rules/async-defer-await.md 2.0 KB
- references/react/rules/async-dependencies.md 1.3 KB
- references/react/rules/async-parallel.md 654 B
- references/react/rules/async-suspense-boundaries.md 2.5 KB
- references/react/rules/bundle-barrel-imports.md 2.3 KB
- references/react/rules/bundle-conditional.md 949 B
- references/react/rules/bundle-defer-third-party.md 920 B
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.
- 22d ago First seen · 47 lines · 52 tokens per session scan A 916e5e40f9f6
best-practices is a skill published in the GitHub repository FradSer/dotclaude (593 stars, last pushed 7d ago), licensed MIT. It adds 52 tokens to every session and 472 once invoked, about $0.0002 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 2026-09-24.
Other skills, from other repositories
splitting-oversized-modules
Split an oversized Python module (a thousand-plus-line logic.py, models.py, api.py, or its test file) into a package of one module per concern, mechanically and provably without changing behavior. Use on a request to split / break up / decompose a god module or move functions out of one, once a human has agreed to…
plankton-code-quality
Write-time code quality enforcement using Plankton — auto-formatting, linting, and Claude-powered fixes on every file edit via hooks.
verify-language
Language-specific verification for Python, TypeScript/JavaScript, and Go. Checks type safety, language idioms, and best practices. Use when asked to "verify language", "check types", or for language-specific checks.
find-type-gaps
Identify functions, methods, and modules missing type annotations in gradually-typed languages (Python, TypeScript, JavaScript), ranked by public visibility and churn.
kieran-python-reviewer
Reviews Python code with an extremely high quality bar for Pythonic patterns, type safety, and maintainability. Use after implementing features, modifying code, or creating new Python modules.
no-bare-casts
Writing as in TypeScript or TSX production code, modifying a file that contains a bare as cast, silencing a type error with a cast, encountering as unknown as, or reviewing a cast site.