dsh-ponytail
Lazy senior dev minimal-code ruleset and prompt skills for DeepSeek Harness.
Install
$ dsh plugin --profile web add link:$(pwd)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 session-level minimal-code system prompt rulesets across Lite, Full, Ultra, and Off modes
- Provides /ponytail command to inspect status, toggle intensity levels, or persist user-level default modes
- Offers /ponytail-review skill to identify overengineering in recent changes
- Offers /ponytail-audit skill for repository-wide overengineering analysis
- Offers /ponytail-debt skill to compile annotated debt items into a ledger
- Offers /ponytail-gain and /ponytail-help skills for scorecards and reference guides
- Supports hot-reloading user configuration and Cordis profile-level configuration
Useful For
- Preventing AI agents from introducing speculative abstractions, unneeded dependencies, or redundant code
- Auditing and reviewing code diffs or full repositories for over-engineered solutions
- Tracking technical debt tagged via ponytail comments during development sessions
- Enforcing pragmatic YAGNI and standard-library-first design principles during autonomous coding
Who It Fits
- Developers using DeepSeek Harness who want concise, minimal-diff implementations from the model
- Engineering leads enforcing YAGNI and minimalist code quality standards in agent workflows
- DSH users looking to reduce unnecessary agent code churn
Documented Limitations
- Token, latency, and cost reductions are conditional on task complexity and are not guaranteed across all models
- Subagent tool executions do not inherit parent system prompts due to isolation boundaries
- Profile-level Cordis configuration changes require restarting the DSH profile
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.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- MengYuil/dsh-ponytail
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 9b03d3f · 2026-09-20
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
- 11GitHub stars
- Forks
- 2
- Open issues
- 2
- Last commit
- 2026-09-09
- Last release
- 2026-09-09
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
A multi-host method pack for architecture-aware, evidence-verified AI coding workflows in DeepSeek Harness.
View plugin →Local, fast cross-agent memory and session indexing system with DeepSeek Harness integration.
View plugin →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed safety and session audit.
View plugin →Native SQLite-backed local project taskboard plugin and UI for DeepSeek Harness with Agent claim and review flows.
View plugin →