Plugin Claude Code
Plugin marketplace listing 5 plugins: kana-review, kana-spec, suno-composer, kana-code-rpc, anipy-cli.
Plugin Claude Code
Plugin marketplace listing 5 plugins: kana-review, kana-spec, suno-composer, kana-code-rpc, anipy-cli.
Instructions file
Instructions for Linaqruf/kana-code-plugins, covering kana-code-plugins — maintainer instructions, hard rules, workflow, versioning (semver — majors are not rewrite counters) and per-plugin notes.
Plugin Claude Code
Use Claude Code as a natural language interface for anipy-cli — search, play, download, and manage anime from the terminal on Windows. Self-healing dependency repair (uv, scoop, mpv/vlc) with user confirmation, non-interactive execution via Git Bash, and Windows-specific troubleshooting.
Command
Search, play, download, or manage anime via anipy-cli on Windows (auto-repairs missing dependencies).
Skill Claude CodeCodex
This skill should be used when the user asks to play, watch, stream, search, download, or binge anime; continue watching or check anime history; install, setup, configure, update, or fix anipy-cli; change video player or set anime quality; troubleshoot anime playback issues; or mentions anipy-cli by name. Triggers on…
Plugin Claude Code
Display Claude Code activity as Discord Rich Presence. Shows project name, current activity (tool use, thinking, compacting, waiting), model, context usage, cost, git branch, lines changed, agent name, and a repository link button — with PID-based multi-session daemon support.
Hook
Runs when a session starts, executing presence.py via python. From Linaqruf/kana-code-plugins.
Hook
Runs when you submit a prompt, before the agent sees it, executing presence.py via python. From Linaqruf/kana-code-plugins.
Hook
Runs before the agent uses a tool for Edit, Write, Read, Bash, PowerShell, Glob, Grep, LS, Task, Agent, SendMessage, Workflow, WebFetch, WebSearch, NotebookEdit, NotebookRead, AskUserQuestion, TodoRead, TodoWrite, Skill, ToolSearch, EnterPlanMode, ExitPlanMode, TaskCreate, TaskUpdate, TaskList, TaskGet, TaskStop…
Hook
Runs before the context is compacted, executing presence.py via python. From Linaqruf/kana-code-plugins.
Hook
Runs when the agent finishes a response, executing presence.py via python. From Linaqruf/kana-code-plugins.
Hook
Runs when a subagent finishes, executing presence.py via python. From Linaqruf/kana-code-plugins.
Hook
Runs when a session ends, executing presence.py via python. From Linaqruf/kana-code-plugins.
Plugin Claude Code
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.
Skill Claude CodeCodex
Adversarial second-harness review, run inline — for code, a PR, a diff, a plan or design doc, prose docs, a proof, or creative content. Untrusts every claim including its own training, verifies against the repo and the live web, runs tests and validators to ground findings (read-only = no authorship, not no…
Plugin Claude Code
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).
Agent
Use this agent at TWO checkpoints of every /kana-spec engagement — lens A (Scope Check) after the interview and BEFORE drafting, to catch wrong premises at their cheapest point; lens B (Draft Check) on the completed draft before the user sees it. The invocation must state which lens applies. Also re-invoke it cheaply…
Agent
Use this agent at the START of every /kana-spec engagement on an existing codebase (skip only for true greenfield) to map what exists for the subject being specified. Spawn it BEFORE framing or interviewing — its cited map pre-fills the interview and grounds every later claim. For large repos (>200 source files) or…
Command
Write or update a grounded specification for anything — a project, feature, design system, API, or migration. Scout the codebase with agents, run an adaptive interview, adversarially verify the draft, and deliver SPEC.md + CLAUDE.md + prompt.md for compound engineering. Triggers on "create spec", "plan project", "spec…
Plugin Claude Code
Compose Suno AI songs (v5/v5.5) with a craft-reviewed workflow - dual-form style prompts (modular + narrative), mora-accurate Japanese prosody, duet voice casting, and a lyric-critic agent enforcing a checkable composition rubric. Vision-first or guided modes, artist and tier reference composition, albums, variations.
Agent
Use this agent EVERY TIME a full song, album, variation, or continuation draft is finalized, BEFORE delivering it to the user — skip only when the user signaled speed ("quick", "just give me", "no review" or equivalent intent) or the lyric-critic preference is set to never. In album mode it is NEVER skipped. Pass…
Command
Compose Suno AI songs with creative or guided workflow, adaptive preferences, craft review, and session reflection.
Skill Claude CodeCodex
This skill should be used when the user wants to compose songs for Suno AI, write lyrics, create style prompts, or generate Suno metatags. Supports J-pop, K-pop, EDM, ballads, rock, and Latin genres, plus album/EP composition, variations, and song continuations. Also handles reference-based composition ("like…