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-skillsgit 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-skills)<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.
<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>- NVIDIA SkillSpector warn
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.
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 | $0.00077 | $0.05469 |
| Opus 5.5 | $0.00031 | $0.02188 |
| Sonnet 5.5 | $0.00015 | $0.01094 |
| Haiku 4.5 | $0.00008 | $0.00547 |
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 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 — 479 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Skills
Invariant Principles
- No Skill Without Failing Test: Run scenario WITHOUT skill first. Document baseline failures verbatim. Same as code TDD.
- Description Triggers, Not Summarizes: Description = when to load, never workflow summary. Workflow in description causes agents to skip body.
- One Excellent Example Beats Many: Single complete, runnable example in relevant language.
- Keywords Enable Discovery: Error messages, symptoms, synonyms throughout. Future Claude must FIND this.
- Close Every Loophole Explicitly: Agents rationalize under pressure. Each excuse needs explicit counter.
- 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.)
- 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
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.
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 · 479 lines · 77 tokens per session scan A c93cb9df24cc
writing-skills is a skill published in the GitHub repository axiomantic/spellbook (11 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 5,469 once invoked, about $0.0003 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
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
terminal-capture
Automates terminal UI screenshot testing for CLI commands. Applies when reviewing PRs that affect CLI output, testing slash commands (/about, /context, /auth, /export), generating visual documentation, or when 'terminal screenshot', 'CLI test', 'visual test', or 'terminal-capture' is mentioned.
tmux-real-user-testing
A real-user test workflow for Qwen Code's terminal interface, using tmux to drive the program and capture readable screen snapshots. tmux is a tool for running and observing terminal sessions.
agent-reproduce-align
Use after a Codex or Claude Code feature has been implemented in Qwen Code to run the selected reference agent and Qwen Code under the same scenario, capture HTTP and terminal traces, compare request bodies, tool/function schemas, outputs, and iterate until the reproduced behavior is close enough.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
verification-before-completion
Use when about to claim work is complete, fixed, or passing, or before committing or creating PRs.