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-commandsgit 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-commands)<a href="https://agentmods.dev/skills/axiomantic/spellbook/writing-commands"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/writing-commands/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-commands"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/writing-commands.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 | $0.00065 | $0.01240 |
| Opus 5.5 | $0.00026 | $0.00496 |
| Sonnet 5.5 | $0.00013 | $0.00248 |
| Haiku 4.5 | $0.00006 | $0.00124 |
Grade A, and why
writing-commands 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Commands
Announce: "Using writing-commands skill for command creation, editing, or review."
Invariant Principles
- Commands are direct prompts: A command loads entirely into context. No phases, no subagents, no orchestration. The agent reads it and does the work.
- Structure enables scanning: Agents under pressure skim. Sections, tables, and code blocks catch the eye. Prose paragraphs get skipped.
- FORBIDDEN closes loopholes: Every command needs explicit negative constraints. Agents rationalize under pressure. Each excuse needs a counter.
- Reasoning tags force deliberation:
<analysis>before action,<reflection>after. Without these, agents skip straight to output. - Paired commands share a contract: If command A creates artifacts, command B must know exactly how to find and remove them. The manifest format is the interface.
Inputs
| Input | Required | Description |
|---|---|---|
| Command purpose | Yes | What the command should accomplish when invoked |
| Trigger phrase | Yes | The /command-name that invokes it |
| Existing command | No | Path to command being reviewed or edited |
Outputs
| Output | Type | Description |
|---|---|---|
| Command file | commands/<name>.md |
Complete command following schema |
| Review report | Inline | Quality assessment against checklist (review mode) |
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 · 129 lines · 65 tokens per session scan A 6875ca7b5848
writing-commands is a skill published in the GitHub repository axiomantic/spellbook (10 stars, last pushed 2d ago), licensed MIT. It adds 65 tokens to every session and 1,240 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
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.