Plugins

Read-only MCP server over the DSH plugin-certification registry, exposing a plugin certification grade, its snapshot and the five-dimension evidence behind it.

A persistent DevRel workbench for official DeepSeek Harness Discussions: triage, topics and evidence-first reporting.

Test-insight plugin that turns repository facts and change risk into evidence-backed test plans and isolated, reviewable test drafts.

Records scoped workflow rules and correction reminders with bounded evidence, local settings, and optional Brain Hub integration.

Measures what an llm-pi-ai endpoint really accepts — context window from its own model list, output-token limit and reasoning levels read out of its own range errors, image support from a generated test image — then reports declared values that contradict that evidence and rewrites them only after confirmation.

Evidence-first frontend release checks: real-browser content, accessibility, runtime, network, and baseline regression reports with screenshots.

Percent-progress scoreboard docked below the todo pill: tracking_write rows with evidence-bound percents, host-captured git checkpoints with before/after deltas, and pursue/align/dismiss actions that reach the agent as instructions.

Turns attached files into versioned evidence: `search_documents` builds a private local index (SQLite FTS5 after a startup capability probe, dependency-free JS fallback otherwise) and returns compact evidence blocks carrying an exact coordinate — PDF page, PPTX slide, text/DOCX line range, or quoted XLSX `Sheet!Range` — which `read_document` expands only while the content version still matches. Contiguous CJK runs are indexed as overlapping bigrams and queried as phrases, so word order is preserved; uploaded raster images take the native vision attachment path instead.

Percent-progress scoreboard docked below the todo pill: tracking_write rows with evidence-bound percents, host-captured git checkpoints with before/after deltas, and pursue/align/dismiss actions that reach the agent as instructions.

Explicit, evidence-first multi-model consultation for DeepSeek Harness

DSH plugin: dsh-evidence-task-board (npm package: @mkaliezz/dsh-task-board)

AI Agent runtime authorization & evidence verification — tool-call GuardrailProvider, CCS 7-dimension verification standard, MCP/DSH security scanner, SSRF/command-injection/credential-exfil blocking with Ed25519 signed receipts.

DeepSeek Harness plugin for Readproof: stable readproof:// identity, freshness policy, snapshots, per-run manifests, diff, byte-exact replay, and evidence bundles as model-callable tools.

Checks whether a similar dsh plugin already exists before you build one, searching the awesome-dsh-plugin registry and the dsh-plugin GitHub topic and returning ranked matches with evidence.

Lifecycle supervision, evidence-driven audit subagents, safe intervention, and blind acceptance gates for DeepSeek Harness

Evidence-first multi-model coding comparison workbench for DeepSeek Harness

Declarative multi-agent pipeline executor for DeepSeek Harness (dsh): runs a manifest of confined role dispatches with mechanical gates and a machine-written evidence ledger. dsh 声明式多角色流水线执行器：按 manifest 派发受限子代理、机械门禁、机器写证据账本。

Runtime governor for DeepSeek Harness: zero-progress steering, generation-bound verification evidence, evidence-aware completion guarding, and task-profile tool restriction.

An intent-calibrated DSH discussion mode that prevents complex conversations from drifting and turns them into evidence-based next steps.

DeepSeek Harness community Bundle for the BeforeDone evidence gate

Sparkles finance evidence tools with a host-native DeepSeek Harness shell and browser client

Audit an agent harness against the harness-evaluation criteria, with machine-enforced evidence validation.

DeepSeek Harness community Bundle for local, evidence-backed Agent Memory