Find the right DSH plugin
for your next workflow

Disk-usage audit for dsh data directories: total size, per-directory breakdown, largest files, oversized-file warnings (session logs can hit hundreds of MB) and cleanup suggestions — CLI plus an agent-callable disk_audit tool, dsh-disk-audit/v1 reports, zero runtime deps, read-only.

First-run health check for DeepSeek Harness: verifies Node/pnpm/dsh toolchain, home, profile, API key (names only, never values), workspace writability and npm registry, then prints actionable next steps — CLI plus an agent-callable quickstart tool, dsh-firstrun/v1 reports, zero runtime deps.

Generate llms.txt for dsh plugin repositories from package.json + README — AI-readable discovery files, zero runtime deps, read-only by default. CLI plus an agent-callable llms_forge tool.

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 quality scorecard for DeepSeek Harness: 0-100 with grade, 6 components, fix suggestions per deduction, batch leaderboard - CLI plus an agent-callable quality_score tool.

Generate README.md for dsh plugin repositories from package.json + cordis.patch.yml + source layout — install/CLI/tools/dev/license sections, deterministic, zero runtime deps, read-only by default. CLI plus an agent-callable readme_forge tool.

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.

Turn-based time tracking from dsh session logs: totals, per-day/project/provider/source rollups, tool-call counts, failure rates, and time-to-first-token — CLI plus an agent-callable timesheet tool, dsh-timesheet/v1 reports, zero runtime deps.

Plug/unplug any DeepSeek Harness plugin cleanly — list every mounted layer (bundles + patch rows), remove with full cleanup, disable/enable without deleting, and audit for orphaned/dangling state. CLI + agent-callable unplug tool. Read-only by default; destructive operations require explicit confirmation.

Redacts supported secret patterns from the `session-telemetry/record` export copy before configured telemetry backends receive it.

Writes local JSONL summaries of per-turn tool counts and coarse verification signals without storing prompts, tool arguments, or result text.

Appends local hash-chained JSONL receipts for tool results and session events without storing prompts, tool arguments, result text, or raw session IDs.

Authentication gate for the DeepSeek Harness Web UI: login covers pages, /api, /plugins and WebSocket upgrades; PBKDF2 password hashing, HttpOnly SameSite session cookies, IP-based login lockout, a user-management settings panel (users edit their own profile, admins add or remove users and reset passwords), admin-only model and API-key configuration guards, per-user isolation on the REST/list APIs and the WebSocket event streams, session persistence across restarts, a JSONL audit log, and a fail-closed gateway.

Hard-stop consecutive identical tool calls after a configurable streak so the agent cannot spin in place.

Hard-stops further tool calls after a configurable per-session budget is reached.

Agent governance suite: policy-based tool gating (allow/deny/ask with wildcards and priorities), a structured JSONL audit trail, and per-agent token quotas against the host token meter, with state under $DSH_HOME/gov.

Installation safety gate for DSH plugins: antivirus-style scan of install scripts, permissions, secrets and network callbacks on local directories or npm tarballs, returning a BLOCK/WARN/PASS verdict before "dsh plugin add".

Claude Code-style permission rules engine: hard/deny/ask/allow tiers with a hard tier above full access, workspace-scoped rules, wildcard path protection, and a visual staged editor; rules persist in settings.yaml.

Auto-approval permission guard: a middle tier between workspace-write and danger-full-access — auto-allows safe operations inside trust directories, always asks a human for destructive ones, with 11 per-category switches and an audit trail.

Single-bundle security analysis plugin: bootstrap tool narrowing, a domain router, and 25 reverse-engineering tools covering APK, native binary, protocol, malware and LLM samples with on-demand reference docs.

Uses an isolated LLM review to approve or reject DSH sandbox permission requests.

Permission mode between workspace-write and full access: shell commands are checked by deterministic rules and a subagent review; irreversible or system-level actions require explicit approval.

Codex-style auto-review permission mode: adds an auto-review preset that auto-approves safe sandbox escalations, asks on risky or ambiguous ones, and rejects critical unconfirmed operations.

Turn-scoped “Allow for this task” approvals: automatically allow matching `danger-full-access` escalations only for the current task, then expire.