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 tsai09495/matt-pocock-engineering --skill wizardgit clone --depth 1 https://github.com/tsai09495/matt-pocock-engineeringWrote 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/tsai09495/matt-pocock-engineering/wizard)<a href="https://agentmods.dev/skills/tsai09495/matt-pocock-engineering/wizard"><img src="https://agentmods.dev/badge/skills/tsai09495/matt-pocock-engineering/wizard/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/tsai09495/matt-pocock-engineering/wizard"><img src="https://agentmods.dev/badge/skills/tsai09495/matt-pocock-engineering/wizard.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 | $0.00043 | $0.01253 |
| Opus 5.5 | $0.00017 | $0.00501 |
| Sonnet 5.5 | $0.00009 | $0.00251 |
| Haiku 4.5 | $0.00004 | $0.00125 |
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 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wizard
Turn a tedious human-only procedure into a deterministic, reviewable Bash journey. The generated script may open the right pages, explain what to click, capture values without exposing secrets, write approved local configuration, and set approved GitHub Actions secrets or variables.
Implicit invocation authorizes only read-only discovery and an in-chat proposal. It does not authorize creating or running a script, opening a browser, changing permissions, reading existing secret values, writing .env, mutating GitHub, performing a cutover, editing documentation, or committing.
Read quality-baseline.md before any write and use template.sh as the fixed library for an approved script.
Fit gate
Use Wizard only when at least one required step cannot safely be performed by the agent in the current authorization scope:
- a person must use an unfamiliar third-party dashboard;
- a person must authenticate, approve access, or retrieve a credential;
- a human-controlled migration or cutover has manual checkpoints;
- the same manual procedure needs a deterministic, repeatable handoff.
Do not use Wizard for ordinary shell scripts, application code, a simple .env.example edit, a migration the agent is already authorized to run, or an explanation that does not need an executable journey. Work the agent can safely do remains in the normal implementation flow.
1. Discover without secrets
Read repository guidance and public configuration. For setup, inspect .env.example, documentation, framework config, Docker/compose files, and variable names referenced by CI workflows.
If real .env* files exist, discover key names and structure without loading or displaying values. Never copy existing values into context, commands, generated source, a proposal, a test record, or a durable artifact. Prefer examples and secrets.* / vars.* references over real secret-bearing files.
For a transition, establish current state, target state, manual checkpoints, rollback, and irreversible actions. Verify third-party UI paths and commands against current official documentation; do not invent dashboard steps.
What ships with it
2 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 · 92 lines · 43 tokens per session scan A 6b9f2d543e94
wizard is a skill published in the GitHub repository tsai09495/matt-pocock-engineering (2 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 1,253 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
stss
Reduce defensive disclaimers, stacked hedging, and self-protective narration when drafting, rewriting, or auditing proposals, articles, case studies, captions, and other reader-facing prose. Use when defensive wording is requested for review or appears in a draft, including wording the assistant adds. Preserve…
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
corezoid-git-context
Analyzes the current session and updates ext/docs/.md in the Corezoid git mirror for the active stage. Use after corezoid-edit, corezoid-create, or corezoid-review when the session was substantial (processes deployed, new external dependencies discovered, architectural decisions made, issues found or resolved).…