writing-skills

writing-skills is a skill for Claude Code, Codex from axiomantic/spellbook. It costs 77 tokens per session (5,469 once invoked), scanned A, original, MIT.

A guide for creating, editing, and checking coding-agent skills before they are released. It treats a skill like software: test the behaviour first, then improve its instructions and examples.

In plain words
What is it for?
Use it to design new skills, revise existing skills, write trigger descriptions, add examples, and verify skill behaviour before deployment.
Why use it?
It helps catch skills that do not trigger correctly, give incomplete guidance, or leave loopholes for the agent to ignore important rules.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to design new skills, revise existing skills, write trigger descriptions, add examples, and verify skill behaviour before deployment.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/axiomantic/spellbook/writing-skills
Install

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.

Any agent
npx skills add axiomantic/spellbook --skill writing-skills
Clone the repo
git clone --depth 1 https://github.com/axiomantic/spellbook

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for writing-skills

README.md
[![agentmods](https://agentmods.dev/badge/skills/axiomantic/spellbook/writing-skills/github.svg)](https://agentmods.dev/skills/axiomantic/spellbook/writing-skills)
Your own site
<a href="https://agentmods.dev/skills/axiomantic/spellbook/writing-skills"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/writing-skills/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.

agentmods 80×15 button for writing-skills

Your own site · 80×15
<a href="https://agentmods.dev/skills/axiomantic/spellbook/writing-skills"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/writing-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,469 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Rogue Agent · line 3
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
  • high Rogue Agent · line 475
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
  • medium Excessive Agency · line 400
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00077 $0.05469
Opus 5 $0.00039 $0.02735
Sonnet 5 $0.00015 $0.01094
Haiku 4.5 $0.00008 $0.00547

Measured 9d ago against content hash c93cb9df24cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

writing-skills 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (render-graphs.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/writing-skills/SKILL.md · 479 lines

How it starts

The opening of the file, as written. The whole thing — 479 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing Skills

Invariant Principles

  1. No Skill Without Failing Test: Run scenario WITHOUT skill first. Document baseline failures verbatim. Same as code TDD.
  2. Description Triggers, Not Summarizes: Description = when to load, never workflow summary. Workflow in description causes agents to skip body.
  3. One Excellent Example Beats Many: Single complete, runnable example in relevant language.
  4. Keywords Enable Discovery: Error messages, symptoms, synonyms throughout. Future Claude must FIND this.
  5. Close Every Loophole Explicitly: Agents rationalize under pressure. Each excuse needs explicit counter.
  6. Rules Bind to Properties, Not Names: State what makes a thing wrong, then list library-specific spellings as non-exhaustive examples. A rule naming only one library's API voids itself at the next migration. (See: Express Rules Against Properties, Not Library Names.)
  7. Model Versioning Strategy: Prefer general model aliases (e.g. sonnet, flash, pro) over hardcoded version numbers (e.g. claude-3-5-sonnet, gemini-2.5-flash). Hardcoded versions are permitted ONLY when a specific behavior is required that differs between versions.

Shared Skill Principles

Read the full file on GitHub · 479 lines

Files

What ships with it

6 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.

Changes

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.

  1. 9d ago First seen · 479 lines · 77 tokens per session scan A c93cb9df24cc

Subscribe to this mod's changes

writing-skills is a skill published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 5,469 once invoked, about $0.0004 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 2026-09-03.

Related

Other skills, from other repositories

atomic-tdd

Test-first discipline. Auto-triggers on "let's implement X", "add feature Y", "fix bug Z", "write a test for", "implement", "build out", and similar pre-code-change phrases. Iron rule: failing test exists before production code. Skip only for pure docs/config changes with an explicit "skipped because:" note. Explicit…

damusix/atomic-claude · 142 tokens

intent-verify

Verify current requirements against implementation and actual results across a product or change scope, including completed features. Run permissible existing checks and report findings without fixes.

ijust/intent-planner · 33 tokens

pr-test-analyzer

Reviews pull-request test coverage for critical gaps, edge cases, and brittle implementation-coupled tests. Prioritises behavioral coverage over line coverage and rates each finding 1-10 by criticality. Use when reviewing PRs that add or modify functionality and you want to assess whether the accompanying tests are…

jasmedia/cc-pr-reviewer · 67 tokens

k-feat

A feature-delivery workflow that clarifies a specification and moves from a failing behavior check to a passing one.

kunbo928/kflow · 22 tokens

k-implement

A development workflow for implementing an existing specification in slices using TDD, a method where tests are written to guide each change. It does not use a separate Work type.

kunbo928/kflow · 22 tokens

go-testing

Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.

Gentleman-Programming/gentle-ai · 26 tokens