dsh-ponytail
Anti-over-engineering ruleset, six bundled skills, and UI controls for DeepSeek Harness.
Install
$ dsh plugin --profile web add --save-exact @maci0/[email protected]Plugin 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 mode-filtered anti-over-engineering prompt ladder into the system prompt
- Provides six skills accessible via composer commands (/ponytail, /ponytail-review, /ponytail-audit, /ponytail-debt, /ponytail-gain, /ponytail-help)
- Offers runtime mode switching through slash commands, natural language triggers ('stop ponytail'), and model tool calls
- Renders a settings configuration card and a composer status chip in the DeepSeek Harness UI
- Supports multiple strictness levels: lite, full, ultra, review, and off
Useful For
- Preventing AI agents from introducing excessive abstractions, boilerplate classes, and premature factories
- Auditing existing pull requests or codebases for code debt and unnecessary complexity
- Enforcing minimal, standard-library-first implementations during interactive development
Who It Fits
- Software engineers wanting minimal and maintainable code from DeepSeek Harness
- Teams seeking to restrict AI over-engineering and boilerplate generation
Documented Limitations
- The configured mode is process-wide across all agents in the current process
- Spawned external subagents (such as subagent-claude-code or subagent-codex) do not inherit the prompt ladder
- UI localized only for English and Simplified Chinese
- Level switching is not recorded as a replayed session event
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 4 runtime, 14 development, 6 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
- maci0/dsh-ponytail
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin Bundle
- Source checked
- 2426c2b · 2026-10-21
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
- 2026-10-19
- Last release
- 2026-10-19
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 →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 →Native SQLite-backed task management and project board bundle with Web UI and Agent workflow tools for DeepSeek Harness.
View plugin →