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 agentmods add skills/aethrox/doctrine/wizardnpx skills add aethrox/doctrine --skill wizardgit clone --depth 1 https://github.com/aethrox/doctrineWrote 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/aethrox/doctrine/wizard)<a href="https://agentmods.dev/skills/aethrox/doctrine/wizard"><img src="https://agentmods.dev/badge/skills/aethrox/doctrine/wizard.svg" alt="Measured on agentmods" 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 | $0.00064 | $0.00803 |
| Opus 5 | $0.00032 | $0.00402 |
| Sonnet 5 | $0.00013 | $0.00161 |
| Haiku 4.5 | $0.00006 | $0.00080 |
Grade A, and why
wizard 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 3d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wizard
A step a human must perform manually is exactly the kind of task an SOP (standard operating procedure) exists to make consistent: detailed, sequential instructions so the task comes out the same way regardless of who runs it or how many times it's been explained before. This skill's defining constraint: a wizard only contains steps genuinely gated on human authority or judgment; anything the agent can do itself belongs in the agent's own work, not in a script that stops to ask a human to do it.
Phase 1: Scope to human-only steps
Before writing anything, separate the procedure into what the agent can do directly and what actually requires a human: clicking through a third-party dashboard with no API, entering credentials only the human holds, or confirming an action with real-world consequence (a production cutover, an irreversible migration step). Only the second category belongs in the wizard. A wizard padded with steps the agent could have just done is friction added for no reason; it exists specifically for the steps that can't be delegated.
Phase 2: One verifiable action per step
Following SOP discipline, each step is a single, unambiguous action, not a paragraph the human has to parse into sub-steps themselves:
- State exactly what to do: which URL to open, which button to click, which value to copy.
- State the expected outcome, so the human can tell they did it right before moving on, not just that they did something.
- Never bundle two decisions into one step: a step that says "configure X and also decide Y" is two steps wearing one number.
- Write each instruction without em dashes: use a comma, colon, period, or a reworded sentence instead.
Phase 3: Capture and persist immediately
When a step produces a value the rest of the procedure needs (an API key, a generated ID, a URL), capture it right there and write it to where it actually belongs (.env, a secrets store, a config file) rather than holding it in the script's memory for a later step to use. A value captured but not yet persisted is lost the moment the script or the human's session ends; persisting immediately makes the procedure resumable, not just recorded.
What ships with it
1 file 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.
- 3d ago First seen · 42 lines · 64 tokens per session scan A 6a1a94cd11ce
wizard is a skill published in the GitHub repository aethrox/doctrine (18 stars, last pushed 22d ago), licensed MIT. It adds 64 tokens to every session and 803 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
excel-cli
Excel CLI automation skill for Windows workbooks. Use when a coding agent needs token-efficient, scriptable, or unattended Excel automation via excelcli commands. Best for CI/CD, scheduled jobs, batch processing, PowerShell workflows, and bulk workbook edits. Supports Power Query, DAX, PivotTables, Tables, Ranges…
meeting-to-deal
Turn meeting transcripts into deal updates — key points, commitments, and next steps posted to matching CRM deals automatically. Auto-creates contacts for new attendees. Use when someone says "log my meetings to deals", "update CRM from calls", "what did I commit to in meetings", "sync notetaker", "log this meeting"…
aevatar-automation
Aevatar scheduling & workflow automation: scheduledagentcreator (cron/one-shot) for independent scheduled Ornn skill agents and reminders — NOT an alias for Studio Team member automation — the long-running task automation playbook, workflow creation semantics (Scope Workflow vs Ornn publish), agentbuilder lifecycle…
anyr
Use when reading, searching, creating, or updating Anytype documents (objects, spaces, types, properties, files, chats) from the command line with the configured anyr CLI, including JSON output patterns for scripting.
setup-assistant
Guides through installation, configuration, and first-time setup of the Claude Patent Creator system.
inbox-review
Morning inbox workflow -- multi-account scan, thread grouping, priority classification, draft replies.