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 agentmods add commands/linaqruf/kana-code-plugins/anipy-cligit clone --depth 1 https://github.com/Linaqruf/kana-code-pluginsWhat 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 | $0.00022 | $0.01416 |
| Opus 5 | $0.00011 | $0.00708 |
| Sonnet 5 | $0.00004 | $0.00283 |
| Haiku 4.5 | $0.00002 | $0.00142 |
Grade A, and why
anipy-cli 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parse the user's intent from: $ARGUMENTS
Use the anipy-cli skill for all operational knowledge — CLI flags, setup procedures, player routing, configuration, and troubleshooting. Run all anipy-cli operations through the Bash tool (this command is tool-gated to it, and the skill's procedures assume Git Bash semantics).
Execution First, Fix on Failure
Do NOT check dependencies upfront. Run the anipy-cli command directly first. Only if it fails, diagnose and repair using the skill's Dependency Repair Chain. Two rules always apply, even if the skill content is unavailable:
- For each missing dependency, use
AskUserQuestionto confirm before installing — never install silently. - If uv installation fails via both
pwsh.exeandpowershell.exe, STOP. Tell the user: "uv could not be installed because PowerShell is not working correctly. Install PowerShell 7 from the Microsoft Store, restart your terminal, and try again."
Execution
Interpret the user's natural language request and map to the appropriate anipy-cli command.
Always prefix commands with PYTHONIOENCODING=utf-8 and suffix with 2>&1. Without the prefix, the progress spinner dumps a non-fatal UnicodeEncodeError traceback into the output — and printing a non-ASCII anime title can crash the command for real (main-thread encoding error).
Timeouts: Use 60s for search/play commands, 120s for downloads.
Always use -s flag for non-interactive search: anipy-cli -s "query:episode:sub/dub"
Mapping examples:
- "play frieren ep 1" →
PYTHONIOENCODING=utf-8 anipy-cli -s "frieren:1:sub" 2>&1 - "play steins gate episode 3 dubbed" →
PYTHONIOENCODING=utf-8 anipy-cli -s "steins gate:3:dub" 2>&1 - "download one piece 1-10" →
PYTHONIOENCODING=utf-8 anipy-cli -D -s "one piece:1-10:sub" 2>&1 - "download frieren 1-3 to D:\anime" →
PYTHONIOENCODING=utf-8 anipy-cli -D -l "D:/anime" -s "frieren:1-3:sub" 2>&1 - "binge spy x family 1-5 dub" →
PYTHONIOENCODING=utf-8 anipy-cli -B -s "spy x family:1-5:dub" 2>&1 - "play frieren 1-3 and 7" →
PYTHONIOENCODING=utf-8 anipy-cli -s "frieren:1-3 7:sub" 2>&1(multi-range) - "show history" → read
history.jsonfrom anipy-cli'suser_files_path(do NOT use-H, it is interactive and will hang) - "migrate my history to the current provider" →
PYTHONIOENCODING=utf-8 anipy-cli --migrate-history 2>&1 - "what version" →
anipy-cli --version 2>&1 - "change player to vlc" → read and edit config.yaml player_path
- "set quality to 720p" → add
-q 720to the next play/download command
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 · 79 lines · 22 tokens per session scan A 45c70e349040
anipy-cli is a command published in the GitHub repository Linaqruf/kana-code-plugins (4 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 1,416 once invoked, about $0.0001 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 commands, from other repositories
psalm
Command "psalm" from Marcel-Bich/marcel-bich-claude-marketplace, covering credo - the preacher's guide, step 0: run setup (recommended), entry point, credo's own teachings and topic: the credo workflow (end to end).
docs-update
You are executing the /dogma:docs-update command. Your task is to synchronize documentation across README files and wiki articles, ensuring everything is up-to-date.
sanitize-git
You are executing the /dogma:sanitize-git command. Your task is to find and remove AI/Claude traces from git history and fix tracking issues where files that should be excluded are still being tracked.
force
You are executing the /dogma:force command. Your task is to.
session-init
You are the Main Agent in an orchestrated workflow. Read and internalize these working instructions.
cleanup
You are executing the /dogma:cleanup command. Your task is to find and fix AI-typical patterns in the codebase that reveal AI/agent usage.