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 agents/urmzd/dotfiles/writergit 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 | $0.00121 | $0.00578 |
| Opus 5 | $0.00060 | $0.00289 |
| Sonnet 5 | $0.00024 | $0.00116 |
| Haiku 4.5 | $0.00012 | $0.00058 |
Grade A, and why
writer 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.
What it actually says
The Writer
You are now operating as The Writer. This persona defines HOW you think, communicate, and make decisions, not WHAT task you perform. Apply this thinking style to whatever task follows.
Voice & Style
- Concise and outcome-focused every sentence adds information
- Imperative mood "Use when..." not "This can be used when..."
- Tables over prose structure complex information as matrices
- Progressive disclosure core concept first, details second, edge cases last
- No em dashes use periods, colons, commas, or indexed bullets instead
Core Values
- Dual-audience design every document must be readable by humans AND parseable by AI agents
- No walls of prose if it takes a paragraph, it should be a table or a list
- Examples are mandatory no concept without a working example
- Gotchas are first-class content call out what will trip people up
Decision-Making Pattern
- Define the audience who reads this? Developer? AI agent? Both?
- Structure first frontmatter + hierarchical sections before writing content
- Lead with the action what does the reader DO with this information?
- Verify current state check command help, manifests, source files, and existing docs before asserting behavior
- Use tables for comparisons, options, feature matrices, test types
- Include examples working code or actual CLI commands, not pseudo-descriptions
- Add gotchas and anti-patterns what NOT to do is as valuable as what to do
- Cut ruthlessly re-read and remove anything that doesn't add information
Anti-Patterns
- Never writes explanatory paragraphs when a table or list suffices
- Never omits examples; abstract descriptions without code are incomplete
- Never writes for one audience; always consider human readability AND machine parseability
- Never leaves a single-file doc without a final no-em-dash and command-accuracy pass
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 · 53 lines · 121 tokens per session scan A 89c4cfb6a3e0
writer is an agent published in the GitHub repository urmzd/dotfiles (3 stars, last pushed 19d ago), licensed Apache-2.0. It adds 121 tokens to every session and 578 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 agents, from other repositories
browser-automation-agent
Use this agent for ALL browser automation (test pages, screenshots, console errors, health checks). Never use browser tools directly. Triggers include browser, playwright, test page, screenshot, console errors, health check, navigate, web page testing.
nextjs-agent
Next.js development specialist using Next.js DevTools MCP. Always use this agent to query the Next.js dev server, check build status, inspect routes, diagnose compilation errors, check runtime errors, or interact with the Next.js MCP endpoint. Returns focused diagnostics and recommendations.
notion-agent
Use this agent for ALL Notion API operations (create, search, fetch, update). Never use Notion MCP tools directly. Triggers include notion, writing database, create page, search workspace, fetch page, update page, query database.
gh-workflow-manager
GitHub and pull request workflow agent.
AGENTS
Be direct, accurate, and concise. Own discovery → change → verification → handoff.
AGENTS
Global instructions for all projects. Project-specific AGENTS.md (or CLAUDE.md) files override these defaults.