Every DeepSeek Harness plugin

What it is — TMCRA-Agent-Memory is a local graph memory solution for DeepSeek Harness and Codex agents. It recalls evidence from owner-global and current-project scopes before each turn and separately records USER and ASSISTANT messages along with provenance to enable visual atlases and cited knowledge pages.

Who it is for — When using DeepSeek Harness or Codex for agent tasks, TMCRA-Agent-Memory is suitable for retaining cross-session project evidence and provenance. It is not suitable for users who do not wish to set up OpenAI-compatible APIs or local generation models, since it requires manual configuration of these to run the memory service.

Watch out — The sandbox test passed: it was installed in a fresh profile and registered in the harness. The static check indicates it will execute shell commands. No obvious issues were found.

The verdict — I would install it because it requires no TMCRA account or production server.

What it is — Zero-dependency tool providing pure function statistical aggregation for numerical data.

Who it is for — When an agent processes numerical data and requires aggregation analysis. Users only needing single-expression evaluation or row/column structure reporting can use calculator or dsh-tool-csv instead.

Watch out — Sandbox test passed in new profile with successful registration. No obvious issues found. Tool execution involves no file reading, no network access, no process creation, and no state saving.

The verdict — I would install it because it provides capabilities that existing toolchains lack.

What it is — dsh-inspect is a DeepSeek Harness plugin that registers checkup, fix, and review tools through the workflow engine to enable an adversarial check-fix-review loop.

Who it is for — When operating in a DeepSeek Harness profile equipped with the workflow engine to trigger checkup fix review tasks via tool descriptions, this plugin provides the integration. If you do not require orchestration using the official workflow engine, then this plugin is not necessary.

Watch out — Sandbox testing passed: installed in a fresh profile and registered successfully by DeepSeek Harness with no runtime exceptions. No obvious issues were found.

The verdict — I would install this plugin because it reuses the official DeepSeek Harness workflow engine for adversarial loops, but only if the profile includes the workflow provider.

What it is — Adds a persistent memory layer to DeepSeek Harness plugins.

Who it is for — When developing agents in DeepSeek Harness that require cross-tool context memory, this plugin is suitable. If you are using other non-DSH platforms, you can skip installing this plugin.

Watch out — Sandbox test passed, no obvious issues found. Historical DSH sessions are not backfilled yet. It only captures new sessions while active.

The verdict — I would install it because it solves persistent memory needs in DSH, but only if nmem CLI is available and for new sessions.

What it is — dsh-spend adds a floating panel to the DeepSeek Harness web UI that displays token usage and estimated spend with per-model, per-day, and per-session statistics.

Who it is for — Developers using DeepSeek Harness for multi-model token tracking would find the panel useful for cost monitoring and billing estimates. Users who do not need UI-based token spend tracking can skip it as it focuses solely on usage metrics rather than general tooling.

Watch out — It passed sandbox testing in a fresh profile and registers successfully with Harness. Static checks note it executes shell commands, but no major issues were found in testing.

The verdict — I would install it if I need to analyze token spends across models and sessions, as it provides direct integration with the UI for real-time stats.

What it is — Provides a skill for AI agents to write long-form Chinese screenplays using background and character bible inputs to generate story continuity.

Who it is for — Suitable when using DeepSeek Harness or Claude Code to create long-form Chinese movie scripts that require continuity management and character consistency. Not for users needing only quick short non-Chinese stories, because it focuses on long-form with the causal-value engine.

Watch out — Sandbox test passed with successful registration in a new profile. It executes shell commands.

The verdict — I would install it for the causal-value engine and continuity ledger in long scripts, but only if you accept that it executes shell commands.

What it is — Adds cross-session memory and self-evolution capabilities to DeepSeek Harness.

Who it is for — In scenarios where the DeepSeek Harness agent handles ongoing conversations requiring user preference and event recall, this plugin is suitable. Users who only use DSH native services without needing to add new modules can skip this plugin.

Watch out — Sandbox test passed: successfully installed in a new profile and registered by DeepSeek Harness. It will execute shell commands. No obvious issues found.

The verdict — I would install it because it adds the two missing capabilities to DSH for cross-session memory and skill synthesis, and the sandbox test passed.

What it is — This plugin imports chat histories from claude-code, codex, reasonix, and zcode into DSH sessions.

Who it is for — A user who works with claude-code and wants to import their chat histories into DSH sessions while preserving workspace bindings and tool calls. Users who do not use claude-code, codex, reasonix, or zcode can create sessions directly in DSH.

Watch out — The plugin executes shell commands. Sandbox testing passed in a fresh profile, where it was registered into the DSH profile.

The verdict — I would install it for zcode compaction restore.

What it is — Displays real-time account balance and Beijing time peak/off-peak pricing tide under DeepSeek Harness composer.

Who it is for — When you need to view account balance and model pricing information in DeepSeek Harness web profile, use this plugin. Users not using the DeepSeek Harness web profile can skip it.

Watch out — Sandbox testing passed; installed in a fresh profile and registered by Harness. No obvious issues found. Costs are estimates; official invoice is authoritative.

The verdict — I would install it because it supports custom tidePrices in configuration to adapt to official pricing changes.

What it is — DeepSeek Harness plugin that enables natural language conversation to operate Excel spreadsheets with automatic formula health checks.

Who it is for — When using DeepSeek Harness conversation interface to manage Excel reports, suitable for operational roles handling sales data with profit formulas. If your Excel work is limited to manual editing in local Excel without relying on conversation interface, you don't need to install it.

Watch out — Sandbox test passed when installed in a new profile and registered into harness. Some chart features require Windows with local Excel installed. No obvious issues found.

The verdict — I would install it if I need to automate Excel formula verification and repairs via conversation, because it closes the full loop from understanding to operation to verification and repair.

What it is — This is a client plugin for DeepSeek Harness that makes conversations behave like the deepseek.com web/app chat, supporting in-place editing of prompts, answer regeneration, and per-message version paging.

Who it is for — If you are conducting multi-turn conversations in DeepSeek Harness and need in-place editing of prompts and answer regeneration, this plugin is suitable for you. If you use DeepSeek Harness for other chat styles, you can choose other plugins.

Watch out — Sandbox test passed: installed in a new profile and registered into the profile by harness. Requires source installation and applying two patches to fully use it.

The verdict — If I were you, I would install it because it provides conversation consistency like deepseek.com in DeepSeek Harness, which is worth it.

What it is — Sends DSH event metadata to Tuning Engines for governed AI workflow traces, policy evaluation, cost analysis, and Work Session review.

Who it is for — In DeepSeek Harness workflows involving tool calls, model evaluations, approvals and error handling that require policy evaluation and cost analysis, this plugin is suitable for installation. If your workflows do not involve any tool, approval or error events, this plugin is not applicable.

Watch out — Sandbox test passed in a new profile with successful registration to harness. Requires providing an API key or token. No obvious issues found.

The verdict — I would install it if my workflows need event export for Work Session review because it integrates with Tuning Engines for policy evaluation but only under the premise that tools and retries are involved.

What it is — Make file paths clickable in DSH replies with Codex-style inline open, file manager reveal, and end chip list.

Who it is for — When the agent outputs replies containing file paths in DeepSeek Harness, users who need them converted to clickable links. Users who do not want to use the plugin on Linux or Windows platforms because those platforms have not been tested.

Watch out — Sandbox test passed: installed successfully in a new profile and registered by harness. No obvious issues found.

The verdict — I would install it because it has been fully tested on macOS, but only if the agent uses the required output format.

What it is — This is an Exa web search plugin that supports anonymous MCP fallback.

Who it is for — If you need web search in DeepSeek Harness and want no API key configuration, this plugin is suitable. Users who prefer the official maintained Exa integration can skip installing this plugin, since the official package covers the core features.

Watch out — Sandbox testing passed. It can be installed and registered in a new profile. No obvious issues found.

The verdict — I would install it if the anonymous MCP search rate limits are acceptable, because it provides a feature missing from the official package.

What it is — Provides email tools for DeepSeek Harness agent: list/read/search/send emails, attachment download, folder listing, with presets for QQ, Gmail, Outlook and multi-account support.

Who it is for — If your agent needs to handle emails from QQ or Gmail accounts, dsh-email is suitable. If your work focuses on code generation or data analysis, you don't need this plugin.

Watch out — Sandbox test passed in a new profile with successful registration. Requires providing an API key or token for the email accounts. No obvious runtime issues found.

The verdict — I would install it because it includes a send-approval gate for secure email sending in UI environments.

What it is — dsh-codex-port batch-ports Codex plugins to DSH skills.

Who it is for — It is suitable to install when transplanting Codex plugins in DSH. If using other agents such as Claude Code, you do not need this plugin.

Watch out — It requires the local Codex CLI. Sandbox test passed: installed in a fresh profile and registered into the profile by harness. No obvious pitfalls found.

The verdict — I would install it because it supports batch porting with idempotent skipping.

What it is — This plugin delivers declarative permission rules for DeepSeek Harness, using ordered allow/deny/ask YAML to match tool names, arguments, workspace paths, and agent identity on the tools/pre-execute waterfall, with full audit, dry-run, and hot reload.

Who it is for — When you want to restrict agent tool calls in DeepSeek Harness based on specific rules for names, params, paths, and identity, this plugin is suitable. If your workflows do not require such matching rules or session logging, you do not need to install it, as another angle is that it is designed for complex permission scenarios involving multiple decision layers.

Watch out — Sandbox testing passed after installation in a fresh profile and registration with harness. Static checks indicate it can execute shell commands, but this is only a hint, not a defect. No obvious runtime issues were found.

The verdict — I would install it because the rules-first approach paired with AI reviewer backstop allows deterministic decisions before model involvement, providing a value in auditable tool execution control.

What it is — This plugin provides a management panel for the DeepSeek Harness MCP client, enabling inspection of connection status, registered tools, errors, and reconnect counts through the /mcp command and Settings tab.

Who it is for — When you need to add, edit, or remove MCP server configurations in DeepSeek Harness using the MCP client, you can install this plugin because it offers a Settings tab for those operations and supports tool trial calls. If you only connect a single static MCP server with infrequent changes, you can manage it directly in cordis.yml without installing this plugin.

Watch out — Sandbox testing passed when installed into a fresh profile and registered by Harness. No obvious issues were found.

The verdict — I would install it because it enables trial calls of MCP tools through the official execution pipeline with permission and approval guards, but only when profile modifications require explicit user approval.

What it is — Adds Claude-style skin to DeepSeek Harness Web interface.

Who it is for — Users needing warm artistic UI when using Claude model in DSH Web tasks should install this skin. Users with existing skin configurations do not need this plugin.

Watch out — Sandbox test passed: installed in new profile and registered by harness. No obvious issues found. Interface follows native light and dark themes.

The verdict — I would install it because it provides Claude-style visual elements, but only if I have DeepSeek Harness Web environment.

What it is — Adds archived session browsing, unarchiving, and file deletion to DeepSeek Harness web settings page.

Who it is for — This plugin is suitable when managing archived sessions in the DeepSeek Harness web interface. If you primarily manage sessions through other DeepSeek Harness modules, you do not need this plugin.

Watch out — This plugin passed sandbox testing and was registered into the profile by Harness after installation in a fresh profile. No obvious issues found. It is a pure JavaScript package that requires no build script authorization.

The verdict — I would install it because it supports deleting session files from disk with two-step confirmation.

What it is — The attention reminder plugin for the DeepSeek Harness Web UI.

Who it is for — When using the DeepSeek Harness Web UI to handle sessions, one needs to be reminded of waiting input or unopened sessions. If not using the DeepSeek Harness Web UI for session handling, this plugin is not necessary.

Watch out — The sandbox test passed: in a fresh profile the plugin is installed and registered by harness. No obvious issues found.

The verdict — I would install it because it shares counts from the built-in sessions store for reminders without depending on extra code.

What it is — Integrates DeepSeek account balance query and session spend estimate into top-bar chip and settings card in DeepSeek Harness.

Who it is for — When using DeepSeek Harness for sessions, users who need to monitor account balance and spend estimates are suitable to install this plugin. If you are not using the DeepSeek Harness framework, you can choose not to install it.

Watch out — Sandbox test passed: successfully registered into profile after installation in a new profile. No obvious issues found.

The verdict — I would install it because it provides a self-contained solution without requiring host repository changes.

What it is — Records model request token usage to per-day JSONL files and displays stats charts with per-model breakdown in Web settings page.

Who it is for — In DeepSeek Harness web UI for content generation tasks using DeepSeek models, someone who needs to track token consumption is suitable for installing this plugin. Users not concerned with model pricing details need not install this plugin.

Watch out — Sandbox test passed with installation in a new profile and successful registration. History backfill runs on first startup. No obvious issues found.

The verdict — I would install it because it provides live cost calculation and pricing dialogs based on model rates.

What it is — This is a DeepSeek Harness plugin providing research agent support.

Who it is for — This plugin is suitable for users conducting research tasks using DeepSeek Harness. Users who do not want the plugin to execute shell commands can choose other plugins.

Watch out — The plugin executes shell commands. Sandbox testing has not been conducted. No obvious issues found.

The verdict — I would not install it because sandbox testing has not been conducted yet.