dsh-model-prompt-injector

Automated evidence available

Per-model system prompt injector for DeepSeek Harness: append custom prompt text to the END of the system prompt for locally configured models, matched by exact provider/model route or a provider-wide provider/* rule (both stack in order). A Settings page lists every configured provider and its models for per-route editing with instant effect, and rules persist to DSH_HOME so they survive restarts. Applies to main sessions, subagents, and workflow children alike.

Author: MoonlitDropOfBlood · Models & Providers · Catalog snapshot: 2026-09-19

Canonical semantic path

Models & AI CapabilitiesAgent Behavior Presets & System SteeringSystem Rules & Instruction Injection

One primary path; alternate capabilities remain separate.

What it may solve

Per-model system prompt injector for DeepSeek Harness: append custom prompt text to the END of the system prompt for locally configured models, matched by exact provider/model route or a provider-wide provider/* rule (both stack in order). A Settings page lists every configured provider and its models for per-route editing with instant effect, and rules persist to DSH_HOME so they survive restarts. Applies to main sessions, subagents, and workflow children alike.

Imported third-party catalog description; not a Registry verification conclusion.

What can currently be confirmed

Active analysis coverage 1/5. Historical chains are retained but do not count toward current coverage.

Not analyzed

Source structure

Source structure has not been analyzed.

Not analyzed

Repository health

Repository metadata has not been analyzed.

Not analyzed

npm release

npm release metadata has not been analyzed.

Analysis complete

DSH compatibility

Conclusion: Compatibility verification passed. Installation, profile loading, and sustained startup all completed. Test environment: DSH 0.1.6-alpha.2, web profile.

Analysis complete

Dependency audit

Conclusion: This bounded audit reported 0 known vulnerabilities. It covers only the locked versions and audit source; zero reports is not proof of safety.

Not analyzed

Functional verification

The plugin’s advertised feature has not been automatically verified. Passing installation and startup does not prove that feature works.

Analysis complete

Static risk scan

Conclusion: The scan observed 3 code capabilities: may read environment variables, may create or modify files, may access the network. No predefined elevated-risk condition was triggered; this is not proof of safety.

Analysis complete

Package integrity

Conclusion: Package name, version, entrypoints, and checksum passed validation. Artifact: @duke-dsh-plugins/dsh-model-prompt-injector@1.0.1; SHA-256: 65dce19dcadc470dd9ab815c49c78c52cc9183adcb0b29b7989dba77d202b222.

Automated evidence is scoped to the named artifact, DSH target and profile. It is not a blanket safety or feature-completeness claim.

Continue with the latest plugin manager

Describe your task in a DSH conversation and mention dsh-model-prompt-injector. After installing or updating the manager from npm latest, it can find this candidate through Registry, then inspect its actual source and version locally.

Install or update the plugin manager (latest)

Sources available for local inspection

  • npm package@duke-dsh-plugins/dsh-model-prompt-injectorAnalyzed 1.0.1
  • GitHub sourcegithub:MoonlitDropOfBlood/dsh-model-prompt-injectorExact version not resolved

View source catalog record · View GitHub repository