dsh-write-gate
Commitment write-gate for AI coding agents: two-tier (deterministic + LLM judge) pre-execution policy. Engine-agnostic core with a DeepSeek Harness (dsh) adapter.
290 results
Commitment write-gate for AI coding agents: two-tier (deterministic + LLM judge) pre-execution policy. Engine-agnostic core with a DeepSeek Harness (dsh) adapter.
Toggleable assistant, tool, and Think accents with safe Think Markdown for DSH Web
Ponytail for DSH — the lazy senior dev. Live intensity switching (off/lite/full/ultra) with a toggle in the composer, injecting a minimal-code ruleset before every step to cut token usage.
Controlled A/B comparisons and evidence-backed reports for DeepSeek Harness plugins and presets.
Durable layered memory (global / user / project / branch / daily), confirmation-gated writes, todos and skills. Preserves ~/.dsh/memories files in place with in-place adoption, SHA-256 verified backup and rollback.
Workflow-net runtime for DeepSeek Harness: resource-aware concurrency, native loops and fan-out, static soundness checking before a plan becomes durable, and process mining over its own event log.
Model pricing and capability board for DeepSeek Harness: compare per-1M-token prices, find the cheapest route, and see coding/agentic/vision tags for every LLM you can connect — in the DSH settings UI.
What can this MCP server actually do? Inspect its real capability surface, seal it, and get told when it changes. Never invokes a tool; gives the server a minimal environment.
DeepSeek Harness plugin to heal third-party gateways that omit the stream terminal event (message_stop/done), which otherwise triggers repeated TRANSPORT retries in the dsh agent loop; scope is configurable per provider and per model.
Open-source local browser driver for trusted agents that controls your existing signed-in Chromium browser.
Keeps long coding-agent sessions lean: wrap work in named tasks and, when one is done, fold its whole span into a short titled summary. The conversation stays readable, context costs stay low, and every fold's original content can be read back on demand. For DeepSeek Harness.
AI is great at doing one file. Ditto is for doing the same thing to 30 files without babysitting all 30. Review-first batch automation plugin for DeepSeek Harness: 3 reviewed samples → full preview → approve → safe apply.
Agent-agnostic skill that turns task input files into reusable structural briefs and a per-task searchable index (OpenAI Codex, Claude Code, DeepSeek Harness)
DeepSeek Companion — DeepSeek Harness 官方伴侣插件:对话智能导出、上下文交接摘要、API 成本优化、全局对话检索。
GitHub REST API tools for DeepSeek Harness: repositories, search, issues, pull requests, comments, account binding, and workspace integration, with a browser-side GitHub panel in the web GUI
DSH tool for archiving and reading WeChat Official Account articles via 2100laike WeChat Archive (wx.2100laike.com)
Per-directory context composition for DeepSeek Harness — .dsh/context.yaml declares systemPrompt + preload for every agent loop; memory is a baseline, not a preset
Evidence-backed, human-approved project memory for DeepSeek Harness
Job Hunting DSH plugin and runtime skill scaffold for local job intelligence workflows.
Git source-control sidebar for the DeepSeek Harness web UI: repo init, staging, commit/push/pull, branch & remote management, AI-generated Conventional Commits messages, and a commit-history graph.
Evidence-first frontier AI radar and reproducibility gate for DeepSeek Harness
Authentication and security hardening plugin for DeepSeek Harness
Project stack detection and capability recommendations for DeepSeek Harness.
A safety harness plugin for DeepSeek Harness (DSH): protected-path enforcement, trash-based safe_delete with undo, last-known-good composition snapshots, pre-restart composition checks, and an audit journal.