@zaimokuza/dsh-agent-teams-office
Office views for DSH Agent Teams.
180 results
Office views for DSH Agent Teams.
Group work for DeepSeek Harness: turn one session into a room with a chair and several member agents that message each other and share a task list.
TeamsX for DeepSeek Harness: durable multi-agent teams (captain, members, dependency-aware tasks, mailboxes) with an all-SVG activity panel. Native to dsh 0.1.3-alpha.1 with a capability-detection compat layer.
Matt Pocock's agent skills (mattpocock/skills 1.2.3) as a self-contained DeepSeek Harness plugin: the full 35-skill set ships inside the package and is registered on ctx.skills by a read-only provider, so the set installs, updates and uninstalls as one plugin instead of 35 loose copies.
ETeams for DeepSeek Harness: captain-led multi-agent team collaboration with execution chains, task slots, member dialogs and persistent state
Patient auto-retry for DeepSeek Harness: honor the upstream gateway's retry_after_seconds on a 429 capacity cooldown instead of giving up after two fast retries, and wait out the mislabeled modality 400 a saturated gateway replays from its client-error circuit. Optional floating countdown badge included.
DSH plugin: Codex-style context management — token-budget notice, model-facing new_context, and handoff reset instead of summary compaction.
DSH web client plugin: pins the conversation column to a configurable percentage of its width (default 100%, full width) instead of the built-in 680-920px adaptive reading measure, and ships a card under Settings > Plugins.
Preview and submit actionable GitHub bug reports from DeepSeek Harness
Spreadsheet preview for the DeepSeek Harness web client: .xlsx, .xlsm, .xls, .csv and .tsv files open as a read-only grid in the right Sidebar instead of the unsupported-file placeholder
Write the document a newcomer actually needs on day one: what this project is, how to run it, where things live, the five unwritten rules, and who to ask — discoverable, current, and readable in ten minutes, maintained as the cost of doing the work.
Claim-evidence separation for any document: classifies every checkable claim, traces each to a primary source or a direct measurement, fetches links for real, recounts action-driving numbers, and labels what stays unverified — so a deliverable states its evidence level instead of implying one.