dsh-yunoseek-skin
Yunoseek pink skin for the DeepSeek Harness web GUI (pink --dsw-* token layer, yunoseek brand artwork, assistant avatar) plus the Yunoseek system-prompt injection: the identity prompt rendered as the first system-prompt section.
173 results
Yunoseek pink skin for the DeepSeek Harness web GUI (pink --dsw-* token layer, yunoseek brand artwork, assistant avatar) plus the Yunoseek system-prompt injection: the identity prompt rendered as the first system-prompt section.
Retrieved ≠ injected: CBDC-gated memory for DeepSeek Harness — decides how memory is USED (use/verify/ignore decisions, feedback learning, full audit); local SQLite + FTS5, bounded, no extra model call
Memory protocol enforcement plugin for DeepSeek Harness — forces memory_weave before tool calls, auto-ingests session turns, injects memory context into agent steps. Bridges the opencode-memory MCP server with a hard protocol gate.
Mobile adaptation for the DeepSeek Harness Web UI: compact typography, drawer sidebar, two-page settings, responsive tables and stats, safe touch targets. Pure CSS injection, no source modification.
Mid-turn user steering for DeepSeek Harness: /steer (visible) and /inject (quiet context notice) slash commands, a model-facing mid-turn guidance prompt section, and an always-visible injection bar above the composer.
Inject a configurable dsh-ui status card instruction before every DSH agent reply
A DeepSeek Harness plugin that integrates claude-mem: query, context injection, manual save, and session lifecycle over a local claude-mem worker's HTTP API
Collapsible before/after code-diff cards for edit/write tool calls in DeepSeek Harness (dsh), with absolute line numbers. Pure visual, injected into the conversation flow.
Mingleng mcpguard for DeepSeek Harness 鈥?the first security plugin for DSH. Scans skills and MCP configs for prompt injection, homoglyphs, hidden Unicode, dangerous shell and credential leaks.
DeepSeek Harness plugin + LAN bridge: injects a crypto.randomUUID polyfill so the harness web UI works over plain HTTP from phones (no certs, no public tunnels, works on old iOS). Install as a dsh plugin, or run the standalone proxy via the CLI.
DSH web plugin: right-side context-and-files panel (directory browser, injected-context documents, read-only git commit graph) plus the session-log download action
Auto-capture key decisions from dsh sessions into a versionable DECISIONS.md and inject them into future sessions
Project-scoped AI memory: records pitfalls and user habits per project, injects them into future conversations
Scan agent skill packages for static security risks. Use for skill audit, security check, prompt-injection review, suspicious scripts, unsafe dependencies, zip package review, and pre-install skill review. Not for runtime monitoring.
A safe external-skill discovery and adoption bundle for DeepSeek Harness
Claude Code-style long-term memory for dsh: markdown memory files with frontmatter, MEMORY.md index, session-start prompt injection, and a memory tool.
My Habits for DeepSeek Harness: edit the user-global AGENTS.md from the Web settings — injected into every session by the built-in agent-instructions loader.
Web settings surface for DeepSeek Harness: a force-directed relationship graph of client plugins — inject dependencies and slot registrations. / DSH 设置页插件关系图谱(力导向图)。
Hot-pluggable rollback visualization for the dsh web GUI: turn-anchor badges injected into the trajectory view, click-to-rollback with confirmation, auto-activation of the derived child session
NoAtMark text hygiene as a DeepSeek Harness (dsh) plugin — sanitize untrusted text, scan invisible characters, clean LLM formatting, and escape CSV formula injection.
Thread session memory for dsh — lossless event capture + status-card injection (dsh plugin, standalone repo).
Task-to-skill pairing with a laziness ladder and a safe install cellar. Never overpours, never serves untasted. DSH · Claude Code · Codex
DeepSeek Harness plugin (temporary, pre-upstream-fix): automatically injects a CPython tempfile shim (PYTHONPATH -> sitecustomize) into every confined shell command on the Windows sandbox, so python/pytest tempfile use works with zero extra tools, zero model-context overhead, and zero escalation.
Inject WSL/Windows path and shell facts into the DeepSeek Harness system prompt.