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 parisgroup-ai/imersao-ia-setup --skill launch-auditgit clone --depth 1 https://github.com/parisgroup-ai/imersao-ia-setupWrote 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/parisgroup-ai/imersao-ia-setup/launch-audit)<a href="https://agentmods.dev/skills/parisgroup-ai/imersao-ia-setup/launch-audit"><img src="https://agentmods.dev/badge/skills/parisgroup-ai/imersao-ia-setup/launch-audit/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/parisgroup-ai/imersao-ia-setup/launch-audit"><img src="https://agentmods.dev/badge/skills/parisgroup-ai/imersao-ia-setup/launch-audit.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 | $0.00233 | $0.05388 |
| Opus 5 | $0.00117 | $0.02694 |
| Sonnet 5 | $0.00047 | $0.01078 |
| Haiku 4.5 | $0.00023 | $0.00539 |
Grade A, and why
launch-audit 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 11d 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 — 564 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-Launch Quality Audit
How to Use
This skill activates automatically — no special commands needed. Just say what you want in natural language.
Full Audit (reviews the entire app)
Say any of these:
- "faz um pente fino no projeto"
- "está pronto pra lançar?"
- "roda uma auditoria completa"
- "is this ready to ship?"
- "quality check before launch"
- "score the codebase"
What happens: explores the project → runs 7 audit phases (security, functional, domain data, visual, performance, tests, polish) → generates a scorecard with grades and a launch verdict.
Deep Dive (audits one specific flow in detail)
Say any of these:
- "audita o wizard"
- "deep dive no fluxo de checkout"
- "rastreia os dados do onboarding"
- "revisa o fluxo de pagamento"
- "audita o fluxo de cadastro de paciente"
What happens: explores the project → maps every file in that specific flow → traces each data field step by step → audits every button and interaction → checks AI calls and external services → generates a focused report.
Running both
You can run a Full Audit first, then ask for a Deep Dive on a specific flow that needs more attention. They complement each other.
Mode Detection (for the AI)
Detect which mode to use based on the user's request:
Full Audit — user mentions the whole app or general quality:
- → Run Stage 1 (Discovery) → Stage 2 (7-Phase Audit) → Stage 3 (Scorecard)
Deep Dive — user mentions a specific flow, feature, or multi-step process:
- → Run Stage 1 (Discovery) → Stage 4 (Deep Dive) → produce a focused report
Both modes always start with Stage 1 (Discovery) because understanding the project is non-negotiable.
Task Orchestration (How to Execute)
This audit is a long, multi-step process. To keep it organized and automated, you MUST use a task list (TodoWrite / TaskNotes) to orchestrate the execution. Create all tasks upfront, then work through them one by one — marking each as in_progress when you start it, and completed when the report is saved.
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.
- 11d ago First seen · 564 lines · 233 tokens per session scan A 61dd1ce67d7c
launch-audit is a skill published in the GitHub repository parisgroup-ai/imersao-ia-setup (1 stars, last pushed 29d ago), licensed MIT. It adds 233 tokens to every session and 5,388 once invoked, about $0.0012 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 2026-08-31.
Other skills, from other repositories
improve-code-quality
Guided journey from a working-but-untested vibe-coded prototype to a production-ready product with tests, clean structure, a business-rules boundary, and resilience at scale. Orchestrates nine skills phase by phase - working-with-legacy-code, clean-code, refactoring-patterns, software-design-philosophy…
refactoring-patterns
Apply named refactoring transformations to improve code structure without changing behavior. Use when the user mentions "refactor this", "code smells", "extract method", "replace conditional", "technical debt", "move method", "inline variable", "decompose conditional", or "clean up this messy code". Also trigger when…
code-standards-checker
Run the right linting, formatting, and static-analysis commands after changing code, and check it against PHPCS, ESLint, WordPress Coding Standards, or Drupal Coding Standards. Reads the scripts blocks in composer.json and package.json to find the project's own commands, runs auto-fix before check-only and verifies…
pr-review
Review a pull request or analyze local changes before submitting. Checks the diff against what the ticket asked for, then for correctness bugs, and reports only findings that survive a concrete failure scenario and verification against the file. Findings post as inline suggestions, and silence is a valid result.…
ai-slop-cleaner
A Korean-language cleanup workflow for removing low-quality or unnecessary AI-generated code, with tests used to guard against regressions, meaning new changes that break existing behavior.
review-loop
A staged code-review loop that starts with one reviewer and brings in an architect and critic only when medium-or-more serious findings appear.