dsh-config-watch
Run the following command in DeepSeek Harness:
dsh plugin install Equinox7379/dsh-config-watch
Paste the following prompt into your AI chat to install this plugin:
Install the plugin in DeepSeek Harness by running dsh plugin install Equinox7379/dsh-config-watch; the source repository is available at https://github.com/Equinox7379/dsh-config-watch .
About this plugin
Tracking down when and what changed in your environment config is one of the most frustrating parts of ops debugging. dsh-config-watch tackles this with an intentionally lightweight design: on every service startup it takes a hash snapshot of the key profile files and the plugin manifest, diffs it against the previous snapshot, and appends any differences to a change log. Only file names and hashes are stored, never file contents, so the disk and privacy footprint is negligible.
To query recent changes, call the config_changes tool, which returns the latest entries (default 20, hard cap 200). All data lives under ~/.dsh/config-watch/, with history.jsonl auto-rotated at 200 entries and last-snapshot.json holding the newest baseline. A failed snapshot merely logs a warning and never blocks startup; the plugin is zero-dependency, defines no custom session events, and exposes no HTTP routes, so it stays completely transparent to your existing workflow.
If your team shares a single profile whose plugin list shifts often, or you manage more than one DeepSeek Harness instance, you know the pain of the vague
Use Cases
- Auditing who modified a shared team profile after an unexpected change
- Tracing back which startup introduced a specific plugin list modification
- Confirming the change history of key profile files during incident investigation
Best For
- Ops engineers managing multiple DeepSeek Harness instances
- Dev teams sharing a single profile configuration
- SRE or compliance teams requiring an environment change audit trail
Related Plugins
Traceable, searchable cross-session memory for AI agents that turns conversation knowledge into a typed knowledge graph and recalls relevant subgraphs instead of replaying full history, natively integrated with DeepSeek Harness.
Gives DSH AI cross-session long-term memory, to-do and skill management, plus multi-session orchestration, external AI delegation, and an infinite canvas that grows with you.
dsh-mnemon is a three-tier, pluggable, Agent-driven memory system for DeepSeek Harness, combining Runtime memory, Project Documents, and replaceable Memory Spaces with nine long-term providers.
An opinionated, zero-infrastructure file-based memory protocol: human-readable markdown files plus a bounded always-loaded index, curation discipline, and no database or embeddings.