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 kzytateishi/spikeee-plugins-marketplace --skill code-reviewgit clone --depth 1 https://github.com/kzytateishi/spikeee-plugins-marketplaceWrote 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/kzytateishi/spikeee-plugins-marketplace/code-review)<a href="https://agentmods.dev/skills/kzytateishi/spikeee-plugins-marketplace/code-review"><img src="https://agentmods.dev/badge/skills/kzytateishi/spikeee-plugins-marketplace/code-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/kzytateishi/spikeee-plugins-marketplace/code-review"><img src="https://agentmods.dev/badge/skills/kzytateishi/spikeee-plugins-marketplace/code-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 | $0.00056 | $0.02496 |
| Opus 5 | $0.00028 | $0.01248 |
| Sonnet 5 | $0.00011 | $0.00499 |
| Haiku 4.5 | $0.00006 | $0.00250 |
Grade A, and why
code-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 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Run a comprehensive code review on $ARGUMENTS (or the current branch if no arguments are provided), leveraging any available AI MCP servers for multi-perspective analysis.
The bar for every finding (read first)
Every finding you report MUST clear the bar in refs/finding-bar.md:
located (file:line), concretely fixable (minimal suggested diff), confident
(high/medium only — drop the rest), and material (correctness / security / data /
spec / explicit convention — never pure style). Prefer fewer, sharper findings: ten
line-anchored issues with fixes beat forty generic observations. This bar is what makes the
review as pointed as an inline PR reviewer instead of a wall of advice.
What the review is built around
The spine of this review is refs/high-signal-checklist.md — the concrete, recurring issues that automated PR reviewers (e.g. GitHub Copilot) flag and that generic "review for quality" prompts miss: spec↔code mismatch, enum/constant hardcoding, nil-on-nullable, time/range boundaries, get-or-insert races, missing indexes, XSS escaping, weak test assertions, message↔logic drift. Walking the diff against every category of that checklist is the primary job (Phase 3.b), and pre-empts the post-PR churn of fixing these one comment at a time.
The perspectives below are secondary lenses — a coverage net so nothing whole-cloth is missed. They are necessary but not sufficient; do not let them turn the review into generic advice. Any finding from a lens still has to clear the finding bar.
| Perspective | Details |
|---|---|
| Architecture | Pattern appropriateness, SOLID principles, consistency with existing architecture |
| Quality | Readability, maintainability, duplication, complexity |
| Security | OWASP Top 10, input validation, authentication, authorization |
| Testing | Coverage gaps, coverage threshold compliance, test case sufficiency (normal/error/edge/boundary), edge cases |
| Performance | Inefficient data fetching, memory leaks, unnecessary computation, algorithmic complexity |
| Conventions | CLAUDE.md / AGENTS.md project convention compliance |
| Consistency | PR description / commit messages / linked issue vs. the actual diff (claimed scope, definitions, DB impact, behavior all match the code) |
What ships with it
3 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 · 226 lines · 56 tokens per session scan A b00ab408a9b7
code-review is a skill published in the GitHub repository kzytateishi/spikeee-plugins-marketplace (5 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 2,496 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.
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.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…