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.
/plugin marketplace add Linaqruf/kana-code-pluginsnpx agentmods add plugins/linaqruf/kana-code-plugins/kana-reviewgit clone --depth 1 https://github.com/Linaqruf/kana-code-pluginsWrote 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/plugins/linaqruf/kana-code-plugins/kana-review)<a href="https://agentmods.dev/plugins/linaqruf/kana-code-plugins/kana-review"><img src="https://agentmods.dev/badge/plugins/linaqruf/kana-code-plugins/kana-review.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
kana-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 3d 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.
What it actually says
{
"name": "kana-review",
"version": "1.1.0",
"description": "Adversarial second-harness review, run inline - for code, PRs, plans, docs, math, and creative content. Untrusts every claim including its own training, web-verifies external facts, runs tests and validators to ground findings (read-only = no authorship, not no execution), and reports them with severity and confidence through a re-review loop to explicit approval. Invoke from a fresh review session.",
"author": {
"name": "Linaqruf"
},
"license": "MIT",
"repository": "https://github.com/Linaqruf/kana-code-plugins",
"keywords": ["review", "code-review", "adversarial", "verification", "second-opinion", "pr-review", "plan-review", "docs-review", "findings", "read-only", "inline", "two-harness"]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 128 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 3d ago First seen · 12 lines scan A 1758610e8dab
kana-review is a plugin published in the GitHub repository Linaqruf/kana-code-plugins (4 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
knowledge-patch
Offline monoplugin that routes three native skills to bundled technology patches through compact generated catalogs.
credo
The mentor framework for Claude Code: a self-contained process layer with per-session modes, a work-item lifecycle with a hard Definition of Done, budget-aware autonomy, visual verification, and safety rules that travel into every subagent.
dogma
Intelligent sync of Claude instructions with enforcement hooks for security and consistency.
get-shit-done
Installer for the Get-Shit-Done workflow system (own secured & frozen fork, markdown skills only) - meta-prompting, context engineering and spec-driven development.
hydra
Git Worktree management for parallel agent execution - isolated working directories without Git conflicts.
slopmop marketplace
Slop-mop quality gates as a Claude skill — directed remediation for AI-assisted codebases.