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 AxGord/claude-workflow --skill preferencesgit clone --depth 1 https://github.com/AxGord/claude-workflowWrote 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/axgord/claude-workflow/preferences)<a href="https://agentmods.dev/skills/axgord/claude-workflow/preferences"><img src="https://agentmods.dev/badge/skills/axgord/claude-workflow/preferences.svg" alt="Measured on agentmods" 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 | $0.00007 | $0.01327 |
| Opus 5 | $0.00003 | $0.00664 |
| Sonnet 5 | $0.00001 | $0.00265 |
| Haiku 4.5 | $0.00001 | $0.00133 |
Grade A, and why
preferences 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 6d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User's personal coding preferences
These rules are set by the user through direct feedback. They ALWAYS take priority over base skills.
Model usage
- Use Opus or Sonnet for subagents
- Never use Haiku — quality too low for real work
Linter-owned defaults
The machine-checkable preferences (immutability, member order, explicit
visibility, _-prefix naming, magic numbers, ternary returns, no swallowed
exceptions, dead-weight removal) live as compilable lists in the user's
preferences-lint skill and are compiled into each project's lint config
by lint-setup. The PROJECT's lint config is authoritative — write to
satisfy it; the linter is the correction net. In a project with no lint
config (and where lint-setup is not installed), load preferences-lint
deliberately if the machine-checkable details are needed; if
preferences-lint is ALSO unavailable on this machine, these categories
have no substitute text — say so in the report instead of silently
proceeding without them.
Field initialization
- Initialize fields at the declaration site when the value does NOT depend on constructor parameters
- Only assign in the constructor when the value requires constructor args or complex logic
- This applies to all languages:
final _bg:Sprite = new Sprite(),readonly List<int> _items = new(), etc.
Naming
- Event listener methods: use
Handlersuffix, notonprefix — e.g.frameSelectHandler, notonFrameSelect
Comments and documentation
- All code comments and documentation must be in English only — no other languages in source code
- Empty line before a doc comment (
/** */) on a field — visually separates documented members - Comment only when behavior is non-obvious from the code. Don't paraphrase the line above; don't restate what the type/name already says
Formatting
- No curly braces
{}for single-line bodies (if, for, function, etc.) — reduces visual noise - Combine
for+ifintofor (...) if (...) {— preferred overif (!cond) continue;inside loop body. Guard reads naturally,continueinverts the condition and wastes a line
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.
- 6d ago First seen · 99 lines · 7 tokens per session scan A 05b3657dc7f8
preferences is a skill published in the GitHub repository AxGord/claude-workflow (5 stars, last pushed 1mo ago), licensed MIT. It adds 7 tokens to every session and 1,327 once invoked, about $0.0000 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…