Plugins

Release gate for AI answer quality. Two channels: replay an existing VeriScope archive through the original Python quality gate, or run a threshold gate over a Ragas per-row export with Node only — no VeriScope, Python or pandas. Returns PASS, FAIL or REVIEW with source evidence and a re-checkable receipt; supports per-row thresholds and exact decimal comparison. It never re-evaluates and never calls a model, and REVIEW never becomes PASS.

Multi-model deliberation pipeline for DeepSeek Harness: independent proposals, blind peer review, program-executed evidence verification, immutable revision and independent acceptance on a fresh context.

A mandatory 7-step plan on every request, each step with a binary acceptance criterion, executed through worker subagents and validated by independent memoryless verifier subagents that report PASS or FAIL with evidence.

A shareable delivery receipt for a project hand-off. The `ship_receipt` tool measures what it can and records what it was told, then sorts every line into three zones: verified (evidence this run produced and that reproduces elsewhere — a command that actually ran with its exit code, a file hash for a file that is under version control, a scan that found files, a git ref present in the recorded remote), local-only (true on this machine alone — uncommitted changes, unpushed commits, an artifact no one else can see), and unverified (no evidence, including every sentence a human typed). A claim with no evidence keeps its label and leaves the body blank rather than printing the claim; declares the commit and branch, artifact byte sizes and sha256 with PNG dimensions, and the three pre-push checks.

A delivery receipt panel for a project hand-off. One trigger collects the branch and commit, the test and build results, screenshot dimensions with sha256, and the secret-scan verdict, then assigns every line to one of three zones by evidence alone — verified, local-only, or unverified. A claim in the unverified zone keeps its label and prints an explicitly empty slot instead of the claim itself, because a confidently worded sentence with nothing behind it is the exact thing the receipt exists to catch. Test failures and secret-scan hits are still evidence, so they land in the verified zone with a red tone rather than being quietly dropped.

Evidence-list completeness check: maps facts to evidence and reports gaps with rule IDs.

Session-scoped research evidence ledger with sources, linked claims, open questions, and explicit user review; provides a tool, slash command, and conversation panel, with selected-claim Markdown export that omits excerpts, review notes, and local paths by default; does not fetch sources or verify their truth.

Session-scoped delivery receipts for local artifacts: compare current file hashes with a recorded baseline, keep agent claims separate from explicit user acceptance, flag changed or unavailable files, and export a Markdown receipt through a tool, slash command, and conversation panel.

Track conclusions and revisit them when evidence files change.

A headless-first macOS Computer Use driver for DeepSeek Harness with AX-first observations, window-bound multimodal evidence, host-owned approval, and evidence-backed action receipts

Evidence-grade reports beyond a plain export: /transcript writes styled HTML/Markdown/JSON with Mermaid lineage, editor diffs and a turn timeline; /stats prints a cost-aware card; /archive packs the raw JSONL with a metadata manifest, while /transcript --manifest and /bundle add the SHA-256 evidence manifest — full history, any backend.

Make the AI remember how you think, not what you said: actively captures your principles, redlines, and working habits across sessions — with memory capacity, graceful decay, and human-readable reasoning for every entry. 0.7.0 brings an intuitive persona portrait with evidence tracing.

Audits a DSH profile for capabilities nothing consumes: inventories the declared composition rows, counts how often each registered tool and skill is actually called in the session logs, separates calls that were made from calls that returned a result, and reports the ones with no observed consumer. Ships a skill that fixes the evidence-chain format for completion claims.

Automatically orchestrates complex DeepSeek Harness requests. It detects when delegation is useful, builds a dependency-aware plan, assigns bounded researcher, architect, backend, frontend, tester, and documentation workers, collects structured evidence, and sends the results to a final reviewer. The bundle atomically enables the workflow engine and model-facing subagent tools; disabling the plugin disables its complete tool group as well.

Project PDF library with background indexing and cited page highlights for DeepSeek Harness Web

XingTu 26 production-grade AI agent skills, packaged as a DeepSeek Harness (DSH) skills plugin — token compression, code review, safe refactor, migration, evidence review & more. 26 个生产级 SKILL.md 技能，DSH 一键安装即用。

Native Goal Autopilot Harness for DeepSeek Harness (dsh): plan-execute-audit gates, mechanical enforcement, and evidence-bound closeout as an out-of-tree plugin bundle.

DeepSeek Harness plugin for CVE impact retesting: fingerprint a target, judge it against a CVE's affected range, gather passive evidence, and report a verdict with confidence and limitations.

Score a GitHub repo's contribution-friendliness from live merge and maintainer evidence.

Verifiable authorization, execution evidence, and offline delivery verification for DeepSeek Harness

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.