Plugins

Software-engineering method pack for coding agents, with skills for baseline-first planning, systematic debugging, prompt hygiene, verification before completion, and repair/retirement tracking.

Hash-verankerte Tools read/edit/batch_edit/undo_last_edit für DeepSeek Harness (dsh). Jede Zeile erhält einen eindeutigen 3-Zeichen-Hash (A-Za-z0-9), der über Änderungen hinweg stabil bleibt; veraltete oder mehrdeutige Anker werden abgelehnt, niemals unscharf zugeordnet. Undo bleibt über einen Neustart hinweg erhalten

Schreibt lokale JSONL-Zusammenfassungen von Tool-Aufrufzahlen je Runde und groben Verifizierungssignalen, ohne Prompts, Tool-Argumente oder Ergebnistext zu speichern.

Fail-closed-Kanalbrücke für Feishu (Lark): mit einem Bot chatten, dsh-Agent-Runden zurückbekommen. Integration nur über das offizielle Python-SDK (exakt gepinnt); Allowlist mit Deny-by-Default, Verifizierung von Webhook-Signatur/Timestamp/Replay, sitzungstreue Zuordnung je Chat; zweisprachige Doku.

Health checks for DSH plugins: manifest/patch/entry/build/pack/install verification, model-callable plugin_check, profile host-shadowing + BOM detection, environment diagnostics, and poison preflight.

Plugin-Store: maßgeblicher npm-Katalog + kuratierte Awesome-Liste (550+ Plugins, 11 Kategorien), Qualitätsprüfung über das dsh-Feld, offizielle Ein-Klick-Installation via `dsh plugin add/remove`, Zugang über Sidebar und Einstellungen.

Wächter für Engineering-Disziplin: hinterfragt die Anforderungen vor der ersten Änderung, erzwingt Rot/Grün-Testnachweis-Gates und prüft die Lieferung mit einem abgespaltenen Gegenspieler (grill-requirements-Skill + Tool-Policy-Gates).

Analytik zur Sitzungsausführung: Schritte, Tool-Aufrufe, Fehlschläge, wiederholte Aktionen, Token-Nutzung und Verifizierungssignale, dargestellt als Text-/Markdown-/JSON-Berichte.

Multi-agent math problem-solving & verification framework: brainstorm → solver iteration → multi-verifier debate → Verified knowledge base, with checkpoint resume and manual/auto intervention (also ships as an agent preset).

Verifikations-Gates mit echter Berechnung: mathematische Vereinfachung, Logikbeweise, Regex-Validierung, E-Prover-FOL, Zustandsmaschinen-Prüfungen und Code-Reparatur, gestützt auf in Go kompilierte Binärdateien mit vorgefertigten Windows-Executables.

Bundled Xiaohongshu/RED viral-note agent skill: hot-note research, note generation/rewrite, verification, authorized account analysis, QR login and controlled publishing.

Rust dev domain plugin for DeepSeek Harness (dsh): verification pyramid fmt→clippy→build+test→miri+audit(+semver) as model-facing tools + graph-layer governance (anti-Goodhart 8 rules incl. #[allow] density / deleted tests, blind-spot via Cargo.toml & pub

Linux kernel dev domain plugin for DeepSeek Harness (dsh): verification pyramid L1-L4 as model-facing tools + graph-layer governance (anti-Goodhart / blind-spot / patch-conflict) + AGENTS.md contract as a system-prompt section. Plain JS, no build step.

Open plugin marketplace: live GitHub dsh-plugin topic search with per-repo package.json verification (dsh.bundle/dsh.client manifest badges and a verified-only filter), npm-first installs with same-source anti-squatting checks, update detection, and five agent tools for headless use.

Anti-bot HTTP fetch tools hardened by SXS's production scraping stack (millions of requests/day): UA-pool rotation, retry with exponential backoff, anti-bot wall detection (captcha / verification challenges) and adaptive rate limiting — tools: `sxs_fetch` / `sxs_fetch_json` / `sxs_rate_status`.

Turns local markdown and text documents into a queryable knowledge base with hybrid semantic and keyword search, citation verification, and source injection.

Model-agnostic visual-inspection pipeline for text-only agents: page-by-page HTML screenshots plus a ready-made vision-subagent briefing contract (gewu_prep), then source-code truth verification of every finding (gewu_locate); validated on mimo-v2.5 & qwen3.7-plus.

DeepSeek Harness community Bundle for the BeforeDone evidence gate

Conversational DSH plugin finder: four-source unified index, BM25 pre-filter plus LLM semantic ranking, candidates carry evidence grades and local static security audit, safe install flow with post-install verification.

Verification-driven self-evolution loop: failure logs become verified AGENTS.md rules; in-session plugin (evolve_learn / evolve_apply / evolve_touch / evolve_recall), tool-verify gate, rule lifecycle, local recall.

Verification toolkit for DSH agents: evidence-based claim checking against workspace files with line citations, config validation (JSON/YAML), and read-only URL/npm/GitHub submission-readiness probes.

Cordis-native, evidence-driven full-stack engineering workflow: inspect-first planning, explicit verification evidence, and approval-aware gating for sensitive operations.

Multi-agent deep long-form article pipeline skill for DeepSeek Harness, running 7 roles across 5 phases with parallel literature/data/case retrieval, an evidence base, independent audit and human verification gates.

Spec-driven development discipline for dsh: five keel skills (anchor/spec/probe/build/audit), three review tools and six spec templates enforce specs-before-code, assumption verification and scope control.