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/KaelSensei/MagicAIBuilderWrote 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/kaelsensei/magicaibuilder/magic-wand)<a href="https://agentmods.dev/commands/kaelsensei/magicaibuilder/magic-wand"><img src="https://agentmods.dev/badge/commands/kaelsensei/magicaibuilder/magic-wand/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/kaelsensei/magicaibuilder/magic-wand"><img src="https://agentmods.dev/badge/commands/kaelsensei/magicaibuilder/magic-wand.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 | $0.00000 | $0.02756 |
| Opus 5 | $0.00000 | $0.01378 |
| Sonnet 5 | $0.00000 | $0.00551 |
| Haiku 4.5 | $0.00000 | $0.00276 |
Grade A, and why
magic-wand 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 9d 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 — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Magic Wand Command – Deep Expert-Level Problem Solving
When /magic-wand [issue description] is invoked, immediately execute the following steps to perform a comprehensive, expert-level analysis and fix when standard debugging approaches have failed.
Step 1: Load Project Context & Follow All Rules
- Assume the project root as the working directory
- Load and strictly follow ALL Cursor rules from
.cursor/rules/*.mdc:security.mdc- Security requirementstechnical-stack.mdc- React Native/SQLite patternsdocumentation.mdc- Documentation update requirementsversion-management.mdc- Git commit/push workflowgeneral-principles.mdc- Project philosophy
- Read relevant documentation:
README.mdPROGRESS.md- Architecture documents
- Recent changelog entries
- Check current git status and branch
- Review conversation history if available to understand iteration context
Step 2: Understand the Persistent Issue
-
Parse the issue description provided after
/magic-wand -
Analyze the problem deeply:
- What is the exact symptom?
- What should happen vs. what actually happens?
- When did this issue start?
- Has it been worked on before? (check git history)
-
Identify that this is a persistent issue:
- Multiple fix attempts have been made
- Standard debugging approaches haven't worked
- Need for deeper, more comprehensive analysis
-
Set expert-level mindset:
- Take a step back from the immediate code
- Think about root causes, not just symptoms
- Consider system-wide impacts
- Look for indirect causes
Step 3: Comprehensive Context Analysis (Deep Search)
-
Review recent git history (last 20-50 commits):
git log --oneline -50- Identify all recent changes that could impact the issue
- Look for changes in related files, not just the reported file
- Check for configuration changes, dependency updates, refactoring
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.
- 9d ago First seen · 380 lines · 0 tokens per session scan A 109e6724c2c9
magic-wand is a command published in the GitHub repository KaelSensei/MagicAIBuilder (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,756 tokens. 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 commands, from other repositories
fix-issue
Investigate and fix an issue.
review
Review code changes against project conventions.
metrics
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
traces
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
codebase-review
Review an entire codebase for architecture, engineering health, and exploitable risk; generate a prioritized remediation plan, an evidence-anchored system knowledge document, or both.
pg-health
Read-only PostgreSQL health check with pgbot, then a prioritized diagnosis.