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 reviewergit 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/reviewer)<a href="https://agentmods.dev/skills/parisgroup-ai/imersao-ia-setup/reviewer"><img src="https://agentmods.dev/badge/skills/parisgroup-ai/imersao-ia-setup/reviewer/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/reviewer"><img src="https://agentmods.dev/badge/skills/parisgroup-ai/imersao-ia-setup/reviewer.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 | $0.00079 | $0.04239 |
| Opus 5.5 | $0.00032 | $0.01696 |
| Sonnet 5.5 | $0.00016 | $0.00848 |
| Haiku 4.5 | $0.00008 | $0.00424 |
Grade A, and why
reviewer 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 13d 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 — 688 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewer Skill
This skill enforces a structured validation process before implementation and generates formal documentation (ADR/PR) for traceability.
Core Principle
Never implement without explicit approval on significant changes. Document decisions for posterity.
┌─────────────┐ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐
│ Understand │────▶│ Propose │────▶│ Validate │────▶│ Generate │────▶│ Implement │
│ Request │ │ Solution │ │ with User │ │ ADR/PR │ │ (approved) │
└─────────────┘ └─────────────┘ └─────────────┘ └─────────────┘ └─────────────┘
│
▼ (if rejected)
┌─────────────┐
│ Revise │
│ Proposal │
└─────────────┘
When to Activate Reviewer Mode
Always Validate Before:
| Action | Risk Level | Requires ADR | Why Validate |
|---|---|---|---|
| New feature implementation | 🔴 High | ✅ Yes | Wrong architecture is expensive |
| Database schema changes | 🔴 High | ✅ Yes | Migrations are hard to undo |
| API contract changes | 🔴 High | ✅ Yes | Breaking changes affect clients |
| Refactoring > 3 files | 🟡 Medium | ⚠️ Maybe | Scope creep, unintended effects |
| Dependency upgrades | 🟡 Medium | ⚠️ Maybe | Breaking changes, compatibility |
| Security-related changes | 🔴 High | ✅ Yes | Vulnerabilities are critical |
| Performance optimizations | 🟡 Medium | ⚠️ Maybe | Premature optimization |
| Deleting code/files | 🔴 High | ✅ Yes | Data loss, broken references |
| Infrastructure changes | 🔴 High | ✅ Yes | Downtime, cost implications |
| Third-party integrations | 🟡 Medium | ✅ Yes | Vendor lock-in, costs |
Skip Validation For:
- Typo fixes
- Comment updates
- Formatting changes
- Test additions (non-breaking)
- Documentation updates
- Single-line bug fixes (obvious)
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.
- 13d ago First seen · 688 lines · 79 tokens per session scan A 45a39dd1a3c0
reviewer is a skill published in the GitHub repository parisgroup-ai/imersao-ia-setup (1 stars, last pushed 12d ago), licensed MIT. It adds 79 tokens to every session and 4,239 once invoked, about $0.0003 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 2026-10-06.
Other skills, from other repositories
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.
Independent Review Synthesis
A review tool that combines findings from multiple human or AI code reviews and checks them against the diff, surrounding code, tests, and prior findings.
Architecture Validation Plan Guard
Detect missing validation plans (how to verify the design is correct) in design documents and ADRs.
review
Use when asked for an opinionated review of the codebase - architecture/backend findings, UI findings against the project's own design docs, or both - severity-ranked with evidence, written to docs/capstone/review.md. Bare "review" does both sides; "review backend" or "review frontend" does one. "review retro…
semantic-validation
GenAI-powered semantic validation - detects outdated docs, version mismatches, and architectural drift.
han-release
Cut a Han release: update CHANGELOG.md with the changes since the last release, bump and tag every plugin that changed as {plugin-name}--v{version} so a version-constrained dependency can resolve, and publish a GitHub release crediting every merged pull request and closed issue to the people behind it. Use when…