@ttxl314/dsh-skill-lord-serf
DeepSeek Harness plugin: Lord/Serf agent protocol 0.5 skills (file-based multi-agent orchestration with bounded execution and schema-validated submissions)
198 results
DeepSeek Harness plugin: Lord/Serf agent protocol 0.5 skills (file-based multi-agent orchestration with bounded execution and schema-validated submissions)
DSH web plugin: a task kanban that refines requirements into phased plans, auto-executes them in git worktrees (one session per phase), and auto-merges into the main branch on completion.
Graph Monitor plugin for DeepSeek Harness: define and customize GRAPH workflows, then visualize each node live as it executes — Waku-agent style topology chart with animated node/edge status, clickable node details, and a desktop trajectory-like monitor view.
DSH plugin: block dangerous shell commands and secret leakage before execution (tools/pre-execute veto)
Dependency-installation guard for DeepSeek Harness: classifies package-manager commands as ALLOW, ASK, or BLOCK before execution.
Model-facing Everything search tool (es.exe) — blazing-fast file search on Windows via the Everything engine
Agent JIT: a compiler/runtime that offloads deterministic execution paths from LLM agent loops.
Engineering-discipline skill pack for DeepSeek Harness — code review, simplification, plan-then-execute, test-first, and conflict resolution, delivered as a bundled skill provider plugin.
决策地图 (Decision Map) — a DeepSeek Harness bundle plugin that renders the current session's execution trace as a readable timeline plus stat cards.
NeevSandbox execution providers for DeepSeek Harness
Enhanced SSH ops for DeepSeek Harness: adds agent tools the base dsh-ssh plugin leaves uncovered — host testing, remote ls, ~/.ssh/config import, known_hosts fingerprint check and multi-host exec — on top of the shared ssh2 engine.
Claude Code subagent provider with configurable CLI executable path, forked from @deepseek-ai/dsh-subagent-claude-code
DeepSeek Harness advisor plugin: pair a fast executor with a stronger reviewer model for plan / correction / stop guidance.
Pre-install supply-chain provenance checks for DeepSeek Harness plugins: verify the tarball you're about to install matches the source you read, before any code runs. Never executes the audited package.
DeepSeek Harness (DSH) host-layer plugin: detects and auto-fixes Windows PowerShell command syntax mistakes — bash constructs, broken line continuations, pasted prompts, CRLF pollution — then executes the corrected command through the host shell seam under the normal sandbox/approval policy
DSH plugin: turn an agent's execution trajectory into a readable post-mortem report.
Task boundaries for DeepSeek Harness Web: use Focus for execution scope and Persistent Anchors for explicit constraints without rewriting prompts.
Mention a server with @ in a DeepSeek Harness session and run commands on it over SSH, behind a two-tier approval gate that fails closed.
CodeBuddy-style deferred tool loading for DeepSeek Harness: keep tool schemas out of the model context until the model loads them on demand via tool_search / defer_execute_tool.
DeepSeek Harness plugin that turns silent tool failures into loud ones: a tools/post-execute policy that matches warning signatures in successful tool output and blocks the result or attaches a notice
Commitment write-gate for AI coding agents: two-tier (deterministic + LLM judge) pre-execution policy. Engine-agnostic core with a DeepSeek Harness (dsh) adapter.
Out-of-tree DeepSeek Harness bundle: an executable implementation of the Harness Engineering Methodology (HARNESS-METHODOLOGY-SPEC v1.0) — agent-discipline prompt section + artifact scaffolding tool + compliance audit tool.
Budget-LLM pool router for DeepSeek Harness: usage ledger, health tracking, Thompson-sampling adaptive failover across free-tier models, quality tier ladder, executor pool, paid-guard, web panel + reroute badge. 穷鬼路由器。
Maestro Guard — pre-execute safety gate: native DSH approval prompts, parsed command-surface rules, decision journal