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 Anbeeld/WRITING.md --skill writinggit clone --depth 1 https://github.com/Anbeeld/WRITING.mdWrote 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/anbeeld/writing.md/writing)<a href="https://agentmods.dev/skills/anbeeld/writing.md/writing"><img src="https://agentmods.dev/badge/skills/anbeeld/writing.md/writing/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/anbeeld/writing.md/writing"><img src="https://agentmods.dev/badge/skills/anbeeld/writing.md/writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00054 | $0.03611 |
| Opus 5.5 | $0.00022 | $0.01444 |
| Sonnet 5.5 | $0.00011 | $0.00722 |
| Haiku 4.5 | $0.00005 | $0.00361 |
Grade A, and why
writing 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 1mo 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing ruleset
Objective
Write for the actual medium, task, reader, and evidence.
Do not optimize for "sounding human" or beating detectors. Treat prose-quality rules and chatbot-default warnings as overlapping but distinct. Do not convert either into universal bans.
Precedence
Follow higher-authority instructions from the active harness. Within this ruleset, apply every section under this order. A rule's explicit trigger, exception, or non-trigger controls within its level.
- Truth, safety, accessibility, privacy, legal or platform requirements, and non-negotiable safeguards
- Explicit user instructions, including task mode, authorized edit depth, protected content, and output constraints
- Genre and medium norms, including medium routing
- Core rules
- Workflow, output-integrity rules, and required checks as implementation and verification of levels 1-4
- Optional diagnostics, correction patterns, watchlists, and heuristics
Honor requested bullets, structure, neutrality, and other explicit constraints. Preserve required structure even when it looks templated.
Capitalization adds emphasis only. It does not change precedence or create a separate rule class.
Task mode
Identify the requested mode before acting:
- Draft: create text from supplied facts, notes, sources, or a brief.
- Revise: change existing text while preserving meaning and useful voice.
- Audit: report material problems without rewriting unless asked. Return no findings when no material problem exists.
- Transform: change length, format, register, medium, or variety of English while preserving the protected content listed under Preserve meaning during edits.
DO NOT substitute a neighboring task. An audit does not authorize rewriting. Polishing does not authorize restructuring. Shortening does not authorize removing conditions, exceptions, citations, qualifications, or necessary steps.
Do not use surface style to decide whether a human or AI wrote text. Use the provenance rules only when authorship is at stake.
What ships with it
8 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.
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.
- 1mo ago First seen · 230 lines · 54 tokens per session scan A 8ba40af0032c
writing is a skill published in the GitHub repository Anbeeld/WRITING.md (381 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 3,611 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 2026-08-30.
Other skills, from other repositories
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says. Use when editing or reviewing prose for AI tells: not-X-but-Y contrasts, one-line closers, staged openers, forced triads, dashes everywhere, inflated claims, sales language, stock AI words, bold labels, or filler. Based on Wikipedia's…
avoid-ai-writing
Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detect-only mode, an edit-in-place mode for files, an optional voice…
preservation-verifier
Use when the user provides an original and rewritten version, asks whether a rewrite preserved protected content, or wants a deterministic check for code, frontmatter, quotes, tables, links, paths, numbers, headings, and residual AI-pattern regressions.
ai-writing-detector
Use when the user asks to detect, scan, audit, score, or flag AI-writing patterns without rewriting the text, including requests for a deterministic local detector result when the host can execute Node.
avoid-ai-writing-router
Use when a request combines AI-writing audit, rewrite, file editing, voice preservation, false-positive interpretation, verification, or when the user invokes Avoid AI Writing without naming a mode.
voice-preserving-rewriter
Use when the user asks to rewrite, humanize, clean up, or remove AI-isms from text while preserving the writer's voice, facts, intent, structure, register, and protected material.