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 tonyghiani/ai-essentials --skill review-teamgit clone --depth 1 https://github.com/tonyghiani/ai-essentialsWrote 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/tonyghiani/ai-essentials/review-team)<a href="https://agentmods.dev/skills/tonyghiani/ai-essentials/review-team"><img src="https://agentmods.dev/badge/skills/tonyghiani/ai-essentials/review-team/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/tonyghiani/ai-essentials/review-team"><img src="https://agentmods.dev/badge/skills/tonyghiani/ai-essentials/review-team.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 | $0.00055 | $0.02883 |
| Opus 5 | $0.00028 | $0.01442 |
| Sonnet 5 | $0.00011 | $0.00577 |
| Haiku 4.5 | $0.00006 | $0.00288 |
Grade A, and why
review-team 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 10d 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Team
Launch 6 specialized reviewers in parallel, each with a distinct perspective, then consolidate findings into a single prioritized report.
Reviewers
| # | Name | Persona source |
|---|---|---|
| 1 | Code Quality | ../branch-refactor-planner/SKILL.md |
| 2 | Adversarial | reviewers/adversarial.md |
| 3 | Architecture | reviewers/architecture.md |
| 4 | Fresh Eyes | reviewers/fresh-eyes.md |
| 5 | Product Flow | reviewers/product-flow.md |
| 6 | Observability Expert | reviewers/observability-expert.md |
Paths are relative to this skill's own directory. When installed for Claude
Code that is ~/.claude/skills/review-team/, so reviewers/adversarial.md
resolves to ~/.claude/skills/review-team/reviewers/adversarial.md. If a read
fails, ls the skill directory rather than guessing.
Mode detection
- Branch review (default): user says "review team", "review my changes", "comprehensive review"
- Scoped review: user provides a target path or project name, e.g. "review team the streams plugin", "review team src/core/packages/http"
- Plan review: user says "review team plan", "review this plan", or attaches a plan document
When the user provides a scope, use scoped review. When no scope is given and no plan is attached, fall back to branch review.
Workflow
Step 0 -- Check for previous runs
Before gathering context, check if a Review Team Report was already produced earlier in this conversation.
If a previous report exists:
- Extract all findings from the previous report (file paths, line ranges, severity, description).
- Store them as
PREVIOUS_FINDINGS-- you will pass this to every reviewer. - In your message to the user, briefly note: "Re-running review team. Previous findings will be compared against current state."
What ships with it
6 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.
- 10d ago First seen · 291 lines · 55 tokens per session scan A 95b3039bc864
review-team is a skill published in the GitHub repository tonyghiani/ai-essentials (7 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 2,883 once invoked, about $0.0003 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.