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/urmzd/dotfiles/write-codenpx skills add urmzd/dotfiles --skill write-codegit clone --depth 1 https://github.com/urmzd/dotfilesWhat 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 | $0.00112 | $0.01238 |
| Opus 5 | $0.00056 | $0.00619 |
| Sonnet 5 | $0.00022 | $0.00248 |
| Haiku 4.5 | $0.00011 | $0.00124 |
Grade A, and why
write-code 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 yesterday.
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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Practices
Layering: Operational picks that satisfy
review-design(principles) andassess-quality(foundational framework). Use this skill when you need a concrete answer for "what tool/pattern/idiom"; usereview-designwhen reasoning about tradeoffs; useassess-qualityfor the underlying "why."
Development Philosophy
- "How easy is this for a junior to understand, develop, and expand on?"
- Self-documenting code > comments
- Small, focused interfaces > god objects
- Convention over configuration
- Explicit > implicit
Tech Stack
| Category | Tools |
|---|---|
| Languages | Rust, Go, TypeScript/Node 22, Python 3.13, Lua 5.4, Java 21, Haskell |
| Package Managers | cargo, uv (Python), npm/yarn/pnpm, luarocks |
| Formatters/Linters | biome (JS/TS), stylua (Lua), clippy (Rust), golangci-lint (Go), ruff (Python) |
| Observability | opentelemetry (tracing/metrics/logs), structlog + stdlib logging (Python; loguru for scripts only) |
| Editor | Neovim (HEAD) with LSP: ty, ts_ls, lua_ls, gopls, rust_analyzer, jsonls, yamlls, bashls, jdtls |
| Shell | Zsh + Oh My Zsh + Powerlevel10k |
| Terminal Multiplexer | tmux (vi-mode, vim-tmux-navigator) |
| DevOps | Terraform, kubectl, Helm, k9s, AWS CLI 2 |
| Dev Environment | Per-language version manager + direnv + a dotfile manager (my setup: Nix Flakes + chezmoi -- see write-code-portfolio) |
Commit Style
Angular Conventional Commits (validated by CI lint; ship skill handles AI-assisted authoring):
type(scope): lowercase imperative description (max 72 chars)
Types: feat, fix, docs, style, refactor, perf, test, build, ci, chore, revert, bump
Rules:
- Imperative mood ("add", not "added"), no trailing period
- Body explains why, not what
- One logical change per commit, every file in exactly one commit
- Order: infrastructure/config → core library → features → tests → docs
- Footer:
BREAKING CHANGE:,Closes #N,Fixes #N,Refs #N
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.
- yesterday First seen · 104 lines · 112 tokens per session scan A 231780671354
write-code is a skill published in the GitHub repository urmzd/dotfiles (3 stars, last pushed 19d ago), licensed Apache-2.0. It adds 112 tokens to every session and 1,238 once invoked, about $0.0006 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
benchling-integration
Benchling Python SDK and REST API integration for registry entities, inventory, ELN entries, workflows, Benchling Apps, and Data Warehouse queries. Use when automating lab data with benchling-sdk or the v2 API.
astropy
Core Python library for astronomy and astrophysics workflows that need Astropy APIs, including units/quantities, coordinates, FITS I/O, tables, time systems, WCS, and cosmology. Use when implementing or debugging astronomical data analysis code with Astropy.
esm
Comprehensive toolkit for EvolutionaryScale protein language models including ESM3 (generative multimodal design across sequence, structure, and function) and ESM C (efficient embeddings). Use for protein sequence/structure/function tasks, inverse folding, embeddings, variant design, and ESMFold2 structure prediction…
mcp-notion-usage-guide
MCP Notion工具使用指南，包含常见问题解决方案和最佳实践。使用当： (1) 访问Notion数据库view URL出现"URL type view not currently supported"错误， (2) 需要获取数据库schema和表结构信息， (3) 查询数据库中的条目内容， (4) 创建页面时MULTISELECT字段值不存在导致失败， (5) 需要更新数据库schema添加新选项， (6) 开发需要集成Notion数据的自动化工作流， (7) querydatasources/query-database-view返回Business Plan要求错误， (8) 需要在无Business…
scan-commit
Automatically scan the repository for unstaged/untracked changes, group them into logical commits using hunk-level analysis, stage and commit them following Conventional Commits.
create-pr
Rebase from the latest origin/main, squash the commits from it, and then create a PR on github with intelligent commit messages based on staged changes.