Oishikunaare-Moe-Moe-Kyun
Global output house rules for DeepSeek Harness enforcing symbol discipline, emoji bans, kaomoji habits, and an optional moe voice.
Install
$ dsh plugin --profile web add github:Nesarf/Oishikunaare-Moe-Moe-KyunPlugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Injects a global system prompt section across all DSH presets, workspaces, and subagents without editing individual preset files
- Bans checkmark and cross judgment glyphs in both agent outputs and written files to prevent context pollution
- Enforces a strict block-level emoji ban while permitting a configurable Japanese kaomoji palette with over 1100 faces
- Monitors output via agent/pre-step and agent/turn-stopping hooks to provide self-check notices and steering before turns close
- Supports dynamic configuration hot-reloading from $DSH_HOME/agent-house-rules.json without requiring host restarts
- Offers an optional tri-lingual (English, Chinese, Japanese) moe voice layer with multiple personality traits and speech patterns
Useful For
- Preventing context regression and model degradation caused by Unicode checkmark and cross symbols in generated files and chat
- Standardizing conversational tone across multi-agent workspaces using consistent kaomoji styles
- Applying consistent voice personas and character traits across DeepSeek Harness sessions automatically
Who It Fits
- DeepSeek Harness users wanting clean, consistent machine-readable agent outputs free of glyph pollution
- Developers seeking global prompt enforcement across all agent presets and subagents simultaneously
- Anime/Moe subculture enthusiasts wanting personalized conversational voice layers in their assistant sessions
Documented Limitations
- Self-check notices and steering use extra model steps and tokens within bounded session budgets
- Moe voice persona inference over conversations depends on detectable voice markers rather than raw preset introspection
- Prompt prefix size grows if kaomoji library limits are configured excessively high
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 0 development, 1 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- Nesarf/Oishikunaare-Moe-Moe-Kyun
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- f6a51b5 · 2026-10-14
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 0GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-10-14
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Agent skill for DeepSeek Harness that turns ideas, plans, and codebases into interactive architecture diagrams.
View plugin →An ontology-first agent preset and epistemic loop platform for DeepSeek Harness.
View plugin →Persistent multi-model agent teams with dynamic DAG orchestration, run monitoring, and token insights for DeepSeek Harness.
View plugin →Command Code LLM provider bundle for DeepSeek Harness with model catalog, quota tracking, and multi-account rotation.
View plugin →