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.
git 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/commands/axiomantic/spellbook/writing-commands-create)<a href="https://agentmods.dev/commands/axiomantic/spellbook/writing-commands-create"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/writing-commands-create/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/commands/axiomantic/spellbook/writing-commands-create"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/writing-commands-create.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 | $0.00034 | $0.01333 |
| Opus 5 | $0.00017 | $0.00666 |
| Sonnet 5 | $0.00007 | $0.00267 |
| Haiku 4.5 | $0.00003 | $0.00133 |
Grade A, and why
writing-commands-create 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 5d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MISSION
Create a well-structured command file an agent can execute correctly under pressure. Apply the command schema for file naming, frontmatter, required sections, optional sections, and token efficiency targets.
Invariant Principles
- Commands are direct prompts: Loads entirely into context. No subagent dispatch. The agent reads and executes.
- Structure enables scanning: Agents under pressure skim. Use sections, tables, and code blocks over prose.
- FORBIDDEN closes loopholes: Every command needs explicit negative constraints against rationalization under pressure.
File Location and Naming
commands/<name>.md # Imperative verb(-noun): verify, handoff, execute-plan, test-bar
Naming convention: imperative verb or verb-noun phrase (verify not verification, execute-plan not plan-execution, test-bar-remove not removing-test-bar).
Frontmatter (YAML, required)
---
description: "One sentence describing WHEN to use, what it does, and trigger phrases"
---
- Single
descriptionfield (nonamefield in command frontmatter) - Under 1024 characters; include trigger conditions and phrases (
Use when user says "/command-name")
Required Sections (in order)
# MISSION
One paragraph. What this command accomplishes. Concise, specific, no filler.
<ROLE>
[Domain]-specific expert. Stakes attached. One sentence persona, one sentence consequence.
</ROLE>
## Invariant Principles
3-5 numbered rules. Non-negotiable constraints.
## [Execution Sections]
Numbered steps, phases, or protocol. Tables for structured data. Code blocks for commands.
## Output
What the agent should produce/display when done.
<FORBIDDEN>
- Explicit negative constraints, one per line, each a complete prohibition
</FORBIDDEN>
<analysis>Pre-action reasoning prompt.</analysis>
<reflection>Post-action verification prompt.</reflection>
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.
- 5d ago First seen · 172 lines · 34 tokens per session scan A ee6659c4a3ab
writing-commands-create is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 1,333 once invoked, about $0.0002 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.
Other commands, from other repositories
subagent-implementation
Orchestrate implement→review subagent loop until task complete. Reads the approved spec, writes a thin brief to .claude/.scratchpad/, dispatches fresh-context subagents, loops until reviewer signs off, commits per green iteration, then updates repo docs.
documentation
Bootstrap and maintain project documentation surfaces. Two modes: bootstrap (discover doc files, index them in CLAUDE.md) and authoring (scan for unindexed docs, match diff against indexed surfaces, walk stale/incomplete/missing items with Yes/Later/Remind/Skip).
watch-ci
Spawn a background Haiku-backed subagent to watch CI for the current branch (or specified target). Provider-agnostic — the subagent inspects project signals to identify the CI system (GitHub Actions, GitLab CI, CircleCI, etc.) and picks the right CLI. Returns immediately; reports back when CI reaches a terminal state.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
integrate
Analyze and enhance AI artifacts to leverage Subcog memory effectively.
add-command
Add a new slash command to the current plugin.