dsh-infra-bootstrap
Run the following command in DeepSeek Harness:
dsh plugin install Bryan-cmf/dsh-infra-bootstrap
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install Bryan-cmf/dsh-infra-bootstrap in your terminal to install the plugin; full source is available at https://github.com/Bryan-cmf/dsh-infra-bootstrap
About this plugin
In the DSH ecosystem, a full skill invocation relies on vector memory, observability, search, a skill catalog, and the runtime all working in concert. Previously developers had to walk a 7-step SKILL.md pipeline component by component, a verbose process that lacked a single readiness gate to confirm the environment before the next call.
dsh-infra-bootstrap replaces that pipeline with two lightweight tools: infra_status probes each component and prints a per-line status; infra_bootstrap layers a final PASS or WARN verdict on top. Probes span vector-memory record count, sibling tool availability (usage_report, audit_skills, infra_health, mem_save, mem_search, cross_search), skill catalog size, and live agents and sessions, giving a full-stack health snapshot in one call.
It is built for workflow developers, automation engineers, and ops teams working on DSH >= 0.1.0-rc.6. Sibling packages are optional, and any MISSING line tells you exactly what to install next, so there is no need to pre-provision every component before running a check.
Use Cases
- Quickly verify full-stack readiness before invoking a skill
- Pinpoint missing sibling packages via MISSING lines
- Replace the verbose 7-step pipeline with a single health snapshot
Best For
- Developers building automation workflows on DSH
- Ops engineers needing a unified readiness gate
- Teams looking to cut 7-step pipeline troubleshooting overhead
Related Plugins
A method pack that makes AI coding agents plan against your real baseline, prove completion with fresh evidence, and reduce reworks and unsafe changes.
Turns the DeepSeek Harness session into a captain that builds a durable sub-agent team, splits goals into dependency-aware tasks, and coordinates work via direct messages and a live Web UI.
Gives coding agents design judgment, letting Claude Code, Cursor, and 70+ agents generate and iterate high-quality UI, presentations, and graphics right from the terminal.
Run the Pi ecosystem's plugins on DeepSeek Harness, unmodified, via a compatibility layer that implements Pi's public extension ABI on DSH's native services.