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 commands/kaelsensei/magicaibuilder/audit-codegit 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/audit-code)<a href="https://agentmods.dev/commands/kaelsensei/magicaibuilder/audit-code"><img src="https://agentmods.dev/badge/commands/kaelsensei/magicaibuilder/audit-code.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 | $0.00000 | $0.02016 |
| Opus 5 | $0.00000 | $0.01008 |
| Sonnet 5 | $0.00000 | $0.00403 |
| Haiku 4.5 | $0.00000 | $0.00202 |
Grade A, and why
audit-code 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 — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Code Command – Code Quality and Security Analysis
When /audit-code [target] is invoked, immediately execute the following steps to analyze code quality, security, and adherence to project standards.
Skills used: web-performance (PageSpeed and Core Web Vitals — required when the audit scope touches the Next.js front-end; see Step 4b).
Step 1: Load Project Context
- 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 workflow
- Read relevant documentation:
README.mdPROGRESS.md- Architecture documents
- Security guidelines
- Identify the current Git branch
- Determine the audit scope:
- If no target specified: audit entire codebase
- If target specified: audit specific files/directories (e.g.,
src/screens/,src/db/)
Step 2: Understand the Audit Scope
- Parse the target provided after
/audit-code(if any) - Determine audit focus:
- Security: Check for vulnerabilities, unsafe patterns, backdoors
- Code Quality: Check for bugs, anti-patterns, technical debt
- Architecture: Check adherence to project patterns
- Performance: Check for performance issues
- Documentation: Check for missing or outdated docs
- Identify files to analyze:
- TypeScript/JavaScript files
- Database schemas and queries
- Configuration files
- Test files (if applicable)
Step 3: Security Audit (Mandatory)
- Check for security vulnerabilities:
- SQL injection risks in database queries
- Unsafe external API calls (only Moxfield/Scryfall allowed)
- File system access issues
- Prototype pollution vectors
- Unsafe object merging
- Dynamic code execution (
eval,Function, dynamic imports) - Hidden logic or obfuscated code
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 · 295 lines · 0 tokens per session scan A 2a20536a5a89
audit-code is a command published in the GitHub repository KaelSensei/MagicAIBuilder (2 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,016 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
spec-plan
Step 4 of the Vibe-Spec workflow. Generate the high-level plan file for every phase in the V2 phase index, each with a scope + status header, so the user has a complete set of plan files to work from.
spec-phases
Step 3 of the Vibe-Spec workflow. Break the V1 spec into sequential, self-contained phases and append a phase index, producing the final V2 spec.
spec-secrets
Audit a Vibe-Spec app for secrets leaking to the browser. A locked-down, redacting command — a local script reads .env and the built bundle, and Claude only ever sees variable NAMES and pass/fail verdicts. Secret values never enter the model's context.
spec-doctor
Read-only environment health check for the Vibe-Spec stack. Detects your OS and reports which prerequisite tools (Git, Node, pnpm, Docker, uv) are installed, their versions, and what each is needed for. Installs nothing.
spec-implement
Step 5 of the Vibe-Spec workflow. Promote a phase plan to detailed, implement it following the vibe-spec references, then update the docs so the spec reflects reality.
spec-refine
Step 2 of the Vibe-Spec workflow. Critique the V0 spec, fill gaps with clarifying questions, then promote it to a V1 spec that maps each piece of functionality to concrete stack tools using the vibe-spec references.