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 axiomantic/spellbook --skill writing-copygit clone --depth 1 https://github.com/axiomantic/spellbookWrote 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/axiomantic/spellbook/writing-copy)<a href="https://agentmods.dev/skills/axiomantic/spellbook/writing-copy"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/writing-copy/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/axiomantic/spellbook/writing-copy"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/writing-copy.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 | $0.00167 | $0.02392 |
| Opus 5.5 | $0.00067 | $0.00957 |
| Sonnet 5.5 | $0.00033 | $0.00478 |
| Haiku 4.5 | $0.00017 | $0.00239 |
Grade A, and why
writing-copy 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Copy
Reasoning Schema
Before drafting: whose thoughts these are, what the author actually observed, the audience and the piece's one point, and whether a personal voice skill is loaded.
After drafting: every AI tell in the catalog checked against the draft, every claim anchored to a number or an observable behavior, no argument invented that the author did not supply, and the piece handed back for a human edit pass.
Invariant Principles
- The Argument Belongs to the Author: You sharpen and draft; you never supply the point. A piece whose thesis you invented is your writing wearing the author's name.
- Slop Is a Bounded Catalog, Not a Vibe: Every removal names the specific tell it removes. "This sounds like AI" is not a finding until it resolves to an entry you can point at.
- A Claim Without a Concrete Is Not a Claim: Attach a number or an observed behavior. To test a line that sounds good, flatten its cadence and read what remains; if the bare claim collapses into a generality, rhythm was carrying it and the line said nothing.
- Voice Is Borrowed, Slop Removal Is Owned: This skill is voice-neutral. On conflict the author's voice skill wins on register and phrasing; this skill wins on slop.
- Only Demonstrated Edits Become Rules: The catalog grows from real human edits the author made, never from taste you inferred on their behalf.
Overview
A voice-neutral guide for writing outward-facing prose that reads like a human wrote it, not an AI. It does two things: it runs the writing PROCESS (turn rough thoughts into a grounded draft), and it strips AI TELLS (the finite, nameable set of moves that make text read as generated).
It deliberately does NOT supply a person's identity. If the author has a personal
voice skill (for example my-voice-skill), load that too: the voice skill owns who
the author is (register, code-switch, signature phrasings), this skill owns process
and slop removal. Core principle: AI slop is a bounded catalog of tells. Name them,
cut them, and ground every claim in a concrete specific, and the prose reads human.
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 · 181 lines · 167 tokens per session scan A 7015cb59352d
writing-copy is a skill published in the GitHub repository axiomantic/spellbook (10 stars, last pushed 2d ago), licensed MIT. It adds 167 tokens to every session and 2,392 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
orchestration-team
Use when coordinating assignments, selected review boundaries, or blocked work across a rig.
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…
bundle-safety
Bundle transform safety — minification variant selection, consumer-constraint verification, identifier preservation, and namespace re-export coverage for build output.
confirm-failures-are-causally-linked-to-the-task-before-reportin
When delegating a task affected by this skill, include.