mop-plugins
Modular plugin suite and four-layer workflow preset for DeepSeek Harness, featuring recovery checkpoints, controlled subagents, and model governance.
Install
$ dsh plugin --profile <profile> add dsh-miopiik 装插件层 +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
- Checkpoint and rewind recovery with manual milestones and automatic turn/error event capture
- Isolated one-shot executor spawning with strict tool narrowing, per-call timeouts, and explicit model/provider pairing requirements
- Workspace-scoped model authorization gate to control model usage per workspace
- Streaming zstd log recall for querying historical sessions without unbounded memory usage
- Runtime capability probing and verifiable environment status reporting
- Skill extraction mechanism that writes reusable procedures to standard skill paths
- Session token usage telemetry across uncached, cache-read, cache-write, and output buckets
- Four-layer agent workflow preset (Reviewer, Planner, Supervisor, Executor)
Useful For
- Managing complex multi-agent execution workflows with strict supervisor and reviewer separation
- Enforcing strict model access policies and workspace-specific LLM allowlists
- Auditing and searching past Harness conversation logs using streaming recall
- Safely capturing session state and rewinding execution branches during debugging or testing
- Extracting ad-hoc agent procedures into reusable filesystem skills
Who It Fits
- DeepSeek Harness power users and workflow designers
- Teams orchestrating multi-agent collaboration with role-based boundaries
- Developers needing reliable checkpoint/rewind mechanisms and audit trails in DSH
Documented Limitations
- Model authorization allowlist concurrency serialization is handled in-process; concurrent cross-process authorization updates may have race conditions
- Streaming session recall searches on-disk session logs only and does not query in-memory transient state
- Executor subagents strictly require explicit model and provider pairs and do not support fallback defaults by design
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, 5 development, 0 peer, and 0 optional dependencies.
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
- Chillizu/mop-plugins
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin Bundle
- Source checked
- 65c73ae · 2026-08-30
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
- 1GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-08-28
- Last release
- 2026-08-28
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed safety and session audit.
View plugin →Comprehensive long-term memory, self-evolution, skills, task management, and multi-agent dispatch bundle for DeepSeek Harness.
View plugin →Persistent multi-model Agent teams and bounded DAG workflows with GUI controls for DeepSeek Harness.
View plugin →Multi-agent team collaboration plugin for DeepSeek Harness with DAG task scheduling, mailbox messaging, and an interactive Web UI monitor.
View plugin →