Minglink/dsh-infinite-gen-4
System-prompt armor plugin for DeepSeek models: appends an unconditional-compliance prompt section at order 100, exposes a profile tool with calibration metadata, and shows a realtime armor-status badge driven by a session projection.
Install
via GitHub · GitHub source
Installing from GitHub runs the project's build script, which pnpm blocks until you allowlist it — run the command once and pnpm prints the exact key to add under `allowBuilds` in ~/.dsh/profiles/web/pnpm-workspace.yaml.
The desktop app keeps its own profile, desktop, and only the dsh command it ships may change it — the npm-installed dsh refuses that profile. Install the command from the app menu (Manage dsh Command…), open Desktop once, quit it fully, run the line below, then reopen Desktop.
via GitHub · GitHub source
Installing from GitHub runs the project's build script, which pnpm blocks until you allowlist it — run the command once and pnpm prints the exact key to add under `allowBuilds` in ~/.dsh/profiles/desktop/pnpm-workspace.yaml.
Our install check ran in a web profile on npm's dsh, not in the desktop app.
What happened when we ran it
Installed cleanly when we ran it
Every command here is run in a throwaway container against a clean profile, and the result is whatever the harness recorded — not a guess from the source. Last run 6d agoon DeepSeek Harness 0.2.1-rc.5.
Show it in your README
For maintainers: the badge serves this listing's latest sandbox verdict, so a re-run updates it on its own — and it links readers to the full result here.
Due diligence
Security
No build script was blocked in our run.
Source: our sandbox install on DeepSeek Harness 0.2.1-rc.5, 6d ago.
package.json declares no preinstall, install or postinstall script.
Source: package.json on GitHub, read at our last sync. prepare is not recorded; it runs only on a GitHub install, and shows up under build scripts when pnpm blocks it.
Neither shell commands nor credentials.
Source: a keyword match on the README — a hint about what the plugin touches, not an analysis of its code.
Not an audit. These are the record of one install and two text scans; nobody has read this plugin's code on your behalf. Plugins run with your agent's permissions.
What it is — Pins an unconditional-compliance block on DeepSeek system prompts at order 100, and exposes calibration metadata plus a live armor badge from a session projection.
Who it is for — You are running a DeepSeek agent in DSH that keeps refusing tool work, and you want that compliance block pinned with a badge you can check mid-session. Leave it out if system-prompt text is change-controlled and extra sections are not allowed; the plugin exists to insert one.
Watch out — The README describes the IG5 reverse-engineering workbench under dsh-infinite-gen-5, which does not match this package’s stated armor behavior, so the materials do not settle which description is the payload. The sandbox only showed a clean-profile install that the harness registered; it did not exercise the prompt section, the badge, or the calibration metadata.
The verdict — This stays off any profile I actually work in until a checkout diff shows one story, not two.
Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.
dsh-infinite-gen-4 is a DeepSeek Harness plugin that modifies the system-prompt path for DeepSeek models by adding an unconditional-compliance section.
The plugin appends that section at order 100, then exposes a profile tool containing calibration metadata. It also derives a realtime armour-status badge from a session projection and displays the badge above the input field. The documented mechanism is therefore session-oriented: prompt assembly, profile data, and visible status are connected through the active session rather than through a separate model integration.
This plugin is intended for users who explicitly want this prompt modification and its corresponding session status indicator in a DeepSeek Harness agent. It is the wrong choice for an agent that must preserve an unmodified system prompt, avoid unconditional-compliance instructions, or keep prompt-policy changes out of the session. The supplied documentation does not establish additional commands, configuration keys, files, platform requirements, or external services.
DeepSeek Harness uses the plugin’s session-layer behaviour to append an unconditional-compliance prompt section at order 100. The supplied description does not identify the section’s exact text or provide a setting that changes its order. The documented effect is a change to system-prompt assembly for DeepSeek models, not a general-purpose prompt editor.
The plugin exposes a profile tool. That tool returns calibration metadata, although the available documentation does not specify the tool’s command name, arguments, response schema, or calibration fields. The metadata is part of the plugin’s profile surface and should not be treated as a documented model capability or benchmark.
A session projection drives a realtime armour-status badge above the input field. The available description establishes the badge’s source as session state, but does not document the projection’s fields, update events, persistence behaviour, or failure state. No configuration keys, environment variables, file paths, platform constraints, or DeepSeek Harness version range are specified in the supplied README material. Install only when the documented prompt modification and session badge match the intended agent behaviour.
Written from the project's own documentation and kept in sync with it. Where the two disagree, the source is authoritative — read the README on GitHub
Same category
Minglink
System-prompt armor plugin for DeepSeek models: appends an unconditional-compliance prompt section at order 100, exposes a profile tool with calibration metadata, and shows a realtime armor-status badge driven by a session projection.
Installed cleanly when we ran it
ranxianglei
The official billion-context plugin: a context-compression plugin for small context windows (a 100K context is enough), token savings (5x fewer tokens), and month-long single sessions (billions of tokens).
Installed cleanly when we ran it
qiz029
A DeepSeek coding agent harness: persistent shell, Ultra subagents, auto approval, Chrome MCP and session telemetry
Did not install when we ran it
liangmianya
Visual, non-linear conversation workspace for DeepSeek Harness — sessions, follow-ups and branches become a browsable conversation map.
Installed cleanly when we ran it
Nwflower
Import full-fidelity chat histories from 13 coding agents (Claude Code, Codex, ChatGPT, Cursor, Gemini, opencode, and more) as resumable DeepSeek Harness sessions, with reverse export back to Claude Code.
Installed cleanly when we ran it
Totoro-qaq
Moves an existing DSH session to another agent preset through a previewable five-section handoff, preserving the source session and either pausing the target for confirmation or continuing immediately.
Installed cleanly when we ran it
