Borrowing it
Nothing to install: this file belongs to otis22/vetmanager-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/otis22/vetmanager-mcp/main/.codex/skills/super-review/SKILL.mdgit clone --depth 1 https://github.com/otis22/vetmanager-mcpWrote 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/otis22/vetmanager-mcp/super-review)<a href="https://agentmods.dev/skills/otis22/vetmanager-mcp/super-review"><img src="https://agentmods.dev/badge/skills/otis22/vetmanager-mcp/super-review/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/otis22/vetmanager-mcp/super-review"><img src="https://agentmods.dev/badge/skills/otis22/vetmanager-mcp/super-review.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 | $0.00033 | $0.01476 |
| Opus 5.5 | $0.00013 | $0.00590 |
| Sonnet 5.5 | $0.00007 | $0.00295 |
| Haiku 4.5 | $0.00003 | $0.00148 |
Grade A, and why
super-review 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Super Review
Use this skill when the user asks for super-review, deep review, Spark scout review, or cross-model arbitration in this repository. AGENTS.md and .cursor/rules/agent-workflow.mdc are the current source of truth for review gates, budgets, CI and the release train.
Scope and output
- Scopes:
changed(default),related,full,stage:N. - Exploratory report flags
--no-sparkand--no-arbitrationmay be used only when the user explicitly requests a reduced report. They never satisfy a mandatory PRD, visual or committed diff gate; a gate always requires Spark or its documented exhausted-budget rationale and both strong verdicts. - Report:
artifacts/review/{YYYY-MM-DD}-{scope_slug}-stage-{N}.md, unless the user requests a different destination. - Candidate findings: YAML with
severity,reviewer,category,file,lines,problem,why_it_matters,suggested_fix,confidence. Record dismissed recurring findings inartifacts/review/inadequate-findings-index.mdwhen writing a super-review report. - If this skill is used as a workflow gate, its final gate verdict is the schema-valid
findingsJSON from both strong reviewers. A Markdown report or YAML candidate list alone is not a gate verdict.
Multi-role report coverage
For a full super-review report, cover these briefs with bounded passes or explicit sections in the strong prompts: code (semantic and local defects), architecture (boundaries), simplicity (unneeded complexity), docs (verified drift), security (access and secrets), performance-and-reliability (timeouts and load), observability (safe logs and diagnostics), tests (missing failure paths), product (PRD and user-visible behavior), and codex-blindspot (edge cases). Assign current models by the contract below; do not infer model names from a historical role matrix.
Aggregate candidates across roles: deduplicate, verify line references, reject speculative, low-impact, duplicate and pre-existing findings; drop non-meta findings with confidence below 0.4. Preserve all critical/high. If more than 120 remain, retain the highest severity × confidence medium/low up to 120. Record inadequacy reasons in the report or inadequate-findings memory. The strong Astra and Opus verdicts arbitrate disputed material findings; neither a role pass nor Spark alone approves release.
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 Changed · -133 lines · -11 tokens per session 799df2cadb1f
- 1mo ago Changed 8f6b36a3cb1c
- 2mo ago First seen · 188 lines · 44 tokens per session scan A 445cc414b7f5
super-review is a skill published in the GitHub repository otis22/vetmanager-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 1,476 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
code-review
Review code for quality, maintainability, and correctness.
release-pr-review
Review pass on an open release PR (release/ → main) — the step between git-wrapup and release-and-publish when a project releases in gated release PR mode. Reads the PR's commit range through the code-simplifier lens plus a correctness review, verifies whatever an automated reviewer left on the PR, lands fixes as…
code-simplifier
Cleanup pass that edits the working tree — over a session's uncommitted changes, or a named path or whole codebase. Reads git diff (or the named target) and simplifies, consolidates, and aligns code with the existing codebase — modernize syntax, cut unnecessary complexity and slop, consolidate duplicated logic, catch…
code-review
Reviews a supplied code path or diff for correctness, security, maintainability, and style without executing or modifying it.
github-commenting
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.
vibecheck
Use immediately before declaring a task or session done—run the discipline checks that catch scope creep, leftover artifacts, unsolicited refactoring, and inflated prose, and block the completion claim on any failure unless the operator supplies a recorded override reason.