dsh-approve-for-me
Fail-closed AI-assisted approval mode for sensitive DeepSeek Harness operations.
Install
$ dsh plugin --profile web add C:\path\to\dsh-approve-for-me-1.0.0.tgzPlugin 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
- Adds an “Approve for Me” access mode while retaining the workspace-write sandbox.
- Reviews each approval-required action individually and can issue at most a one-time allowed-once authorization.
- Lets users follow the conversation model or select another enabled DSH model as the reviewer.
- Displays allow, deny, and review-failure outcomes alongside the relevant operation.
- Shows review rationale, risk assessment, authorization basis, and the model actually used.
- Fails closed when review context is insufficient, risk exceeds scope, the model fails or returns invalid output, or result recording fails.
- Provides /approve-for-me commands for enabling, disabling, checking status, and setting the reviewer model.
Useful For
- Reducing repetitive manual approval clicks without switching to Full access.
- Using a separate enabled model to review sensitive agent actions.
- Reviewing why an action was allowed or denied directly in the DSH conversation UI.
- Keeping one-time approval decisions visible for later inspection.
Who It Fits
- DeepSeek Harness users running the web profile.
- Users who want model-assisted review while preserving workspace-write sandboxing.
- Teams or individuals who need visible, per-operation approval outcomes.
Documented Limitations
- Requires DeepSeek Harness >=0.1.0-rc.5 and <0.2.0.
- Requires Node.js ^22.19.0 or >=24.0.0.
- Only handles requests for which DSH already requires approval; it does not bypass the sandbox.
- Reviewer-model timeouts, unavailability, invalid output, removed configured models, and recording failures deny the action.
- Using a third-party reviewer model sends a limited review payload to that provider and may incur additional cost.
- Automatic approvals can still be incorrect; the README recommends version control, backups, and least privilege.
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 1 runtime, 36 development, 23 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as GPL-3.0.
A root package.json was captured and can be inspected by the registry.
package.json declares a prepare lifecycle script that may run during relevant package installation workflows.
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
- Hakunm/dsh-approve-for-me
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 60784bf · 2026-09-10
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
- 2026-08-16
- Last release
- 2026-08-16
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 →Native SQLite-backed local project taskboard plugin and UI for DeepSeek Harness with Agent claim and review flows.
View plugin →Persistent multi-model Agent teams and bounded DAG workflows with GUI controls for DeepSeek Harness.
View plugin →Sandbox-first automatic permission policy and intelligent risk classification for DeepSeek Harness.
View plugin →