Install
$ dsh plugin --profile web add dsh-instruction-memoryPlugin 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
- Manage long-term custom instructions directly in the DSH settings panel
- Automatically inject active instructions into system prompts on each turn
- Strict user-only write model with no model-facing mutation tools or automated overwrites
- Configure entry modes (always vs. on-demand) and priority levels (high, normal, low)
- Set character injection budgets with visual usage indicators and priority truncation
- Real-time cross-tab and cross-process updates using Server-Sent Events (SSE) and directory watchers
- Safe storage architecture featuring atomic writes, automatic backups, file locks, and revision tracking
- Export and import instructions as JSON with merge deduplication
- Built-in Host, Origin, and Fetch Metadata validation to guard against DNS rebinding on loopback interfaces
Useful For
- Enforcing persistent language, coding, or formatting guidelines across all DSH chat sessions
- Maintaining domain-specific behavioral constraints without re-entering them in every prompt
- Safely managing custom instructions without risk of the LLM covertly modifying its own memory
Who It Fits
- DeepSeek Harness web users needing persistent custom instructions
- Developers seeking granular control over prompt injection priority and character budgets
- Users concerned with memory security and LLM prompt isolation
Documented Limitations
- Settings GUI requires web profile support, although prompt injection continues working in headless/TUI profiles
- No built-in authentication on API endpoints; requires reverse proxy auth or secure tunnels if exposed beyond localhost
- Character budget to token conversion is an estimated ratio rather than model-native tokenization
- Restricted host compatibility enforcing declared DSH version ranges
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
- HERO476/dsh-instruction-memory
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 7bd2438 · 2026-10-15
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
- 2026-10-15
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Lingshu long-term auditable memory system and cognitive graph for DeepSeek Harness.
View plugin →Persistent semantic memory layer for DeepSeek Harness backed by Markdown and Milvus.
View plugin →Composable, view-based layered memory bundle for DeepSeek Harness with pluggable providers and strategies.
View plugin →Comprehensive long-term memory, self-evolution, skills, task management, and multi-agent dispatch bundle for DeepSeek Harness.
View plugin →