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/marketplacegit clone --depth 1 https://github.com/Linaqruf/kana-code-pluginsGrade A, and why
kana-code-plugins 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 2d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "kana-code-plugins",
"owner": {
"name": "Linaqruf"
},
"metadata": {
"description": "Claude Code plugins by Linaqruf",
"version": "2.1.1",
"pluginRoot": "./plugins"
},
"plugins": [
{
"name": "kana-review",
"source": "./plugins/kana-review",
"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.",
"version": "1.1.0",
"author": {
"name": "Linaqruf"
},
"license": "MIT",
"keywords": ["review", "code-review", "adversarial", "verification", "second-opinion", "pr-review", "plan-review", "docs-review", "findings", "read-only", "inline", "two-harness"],
"category": "productivity"
},
{
"name": "kana-spec",
"source": "./plugins/kana-spec",
"description": "Write grounded specifications for anything — projects, features, design systems, APIs — through an agentic pipeline: codebase scouts with cited findings, an adaptive interview, adversarial draft review, and compound-engineering artifacts (SPEC.md, CLAUDE.md, prompt.md).",
"version": "5.0.0",
"author": {
"name": "Linaqruf"
},
"license": "MIT",
"keywords": ["planning", "specification", "spec", "agents", "adversarial-review", "compound-engineering", "interview", "design-system", "feature-planning", "documentation"],
"category": "productivity"
},
{
"name": "suno-composer",
"source": "./plugins/suno-composer",
"description": "Compose Suno AI songs (v5/v5.5) with a craft-reviewed workflow - dual-form style prompts (modular + narrative), mora-accurate Japanese prosody, duet voice 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.
- 2d ago First seen · 74 lines scan A 1672cc25d036
kana-code-plugins 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.
nevaberry
Public marketplace for Nevaberry plugins.
marcel-bich-claude-marketplace
Plugin marketplace listing 8 plugins: credo, dogma, signal, limit, hydra.
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.