DSH Marketplace

dsh-infinite-gen-3

Minglink/dsh-infinite-gen-3

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.

3,264361JavaScriptNOASSERTIONSource

Install

Add dsh-infinite-gen-3 to DeepSeek Harness

Install into

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.

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 4d agoon DeepSeek Harness 0.2.2-rc.1.

Show it in your README

install verified — dshmarketplace

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

Before you install dsh-infinite-gen-3

  • Source of record: Minglink/dsh-infinite-gen-3 — present in the community registry that DSH's own plugin market installs from.
  • Licensed under NOASSERTION.

Security

What installing dsh-infinite-gen-3 runs

Build scripts

No build script was blocked in our run.

Source: our sandbox install on DeepSeek Harness 0.2.2-rc.1, 4d ago.

Install hooks

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.

README mentions

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.

The AI take

What it is — Pins an unconditional-compliance block onto DeepSeek model prompts, and exposes calibration metadata plus a live armor-status badge.

Who it is for — You are running a multi-step DeepSeek agent inside DSH, the model starts refusing tools mid-run, and you need that compliance lock plus a way to see it is still on. Skip it if the system prompt is your own artifact and you cannot allow an extra unconditional-compliance block at order 100.

Watch out — The sandbox only showed a clean-profile install that DSH registered. It did not check whether the section is actually appended or whether the badge tracks the session projection. The README describes an IG5 reverse-engineering workbench, which is not the same writeup as the listing blurb.

The verdict — I will not drop it into a profile that is already doing work until I have the exact injected text in hand.

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.

What dsh-infinite-gen-3 does

Layered prompt blocks pass through an ordered gate into calibration and session-status projections.

dsh-infinite-gen-3 is a DeepSeek Harness plugin that adds a system-prompt armour layer for DeepSeek models, exposes calibration metadata through a profile tool, and reports its live status in the session UI.

The plugin appends an unconditional-compliance prompt section at order 100. It also provides a profile tool containing calibration metadata. A session projection drives a realtime armour-status badge above the input field, so the displayed state is derived from session data rather than from a static label. The supplied material does not name the profile tool, its arguments, configuration keys, or any files it reads or writes.

This is intended for developers testing or inspecting how a prompt-modification layer affects DeepSeek Harness sessions. It is the wrong choice when an agent must preserve the model’s ordinary instruction hierarchy, or when a project requires documented configuration and tool interfaces before installation. DeepSeek Harness already supplies sessions and a UI; this plugin adds a prompt layer and status presentation rather than a general-purpose analysis tool. The repository README describes a different dsh-infinite-gen-5 reverse-engineering workbench, so its commands, runtime assets, and compatibility notes should not be treated as documentation for dsh-infinite-gen-3.

dsh-infinite-gen-3 documentation

How dsh-infinite-gen-3 behaves

dsh-infinite-gen-3 registers a system-prompt section at order 100. That section is described as an unconditional-compliance prompt for DeepSeek models. The plugin also exposes a profile tool with calibration metadata. A session projection supplies the state used by the realtime armour-status badge shown above the input field.

The available description does not establish whether the prompt section replaces or follows other sections beyond its stated order, nor does it define the projection schema, calibration fields, or badge states.

Configuring dsh-infinite-gen-3

The supplied README does not document configuration keys, defaults, environment variables, or editable files for dsh-infinite-gen-3. The installation metadata identifies the web DeepSeek Harness profile as the installation target, but it does not describe profile-level settings for the plugin.

DeepSeek Harness provides the session and UI context in which the plugin operates. The plugin’s documented mechanism is session-scoped: its status badge is driven by a session projection rather than by a separately described persistent store.

Commands and tools

The upstream summary identifies a profile tool, but gives it no command name, argument schema, return format, or invocation example. No plugin-specific slash command is documented.

The README’s command examples belong to dsh-infinite-gen-5, including /ig5 status, /ig5 engines, ig5_profile, and the ig5_* tool family. They should not be used as dsh-infinite-gen-3 commands.

Requirements and limits

The plugin is described as being for DeepSeek models and DeepSeek Harness sessions. The supplied material does not state a DeepSeek Harness version range, supported operating systems, network behaviour, filesystem paths, or permission requirements. Before enabling it in an agent with sensitive access, verify those details from the plugin source or manifest. Its purpose is prompt modification and status reporting, not reverse engineering or the analysis workflows documented for dsh-infinite-gen-5.

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

Alternatives to dsh-infinite-gen-3

3.6k

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

GitHub sourceJavaScript14d ago

AI review

dsh-infinite-gen-4

What it is — The blurb describes a DeepSeek system-prompt armor plugin; the README is an IG5 reverse-engineering workbench.

Who it is for — If you run DeepSeek models as DSH agents and need a compliance block pinned at order 100 plus a session-projection armor badge, the blurb is the match. If you came for static analysis, native debug, and traffic capture on a sample, that writeup is under dsh-infinite-gen-5 and should not be treated as this plugin.

Watch out — The sandbox only showed a fresh-profile install that the harness registered; prompt mutation and the badge were not exercised. No install-time failure showed up.

The verdict — I will not let a registration-only plugin touch the system prompt of a profile I actually work in.

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.Read the source
Details

billion-context

ranxianglei

1.1k

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

npm packageTypeScript28d ago

AI review

billion-context

What it is — Compresses agent context so small windows can hold long coding sessions, claiming ~100K is enough and roughly 5× fewer tokens.

Who it is for — You're on a ~100K-window model in DeepSeek Harness, dragging one refactor across many days, with context length and token use already against the ceiling. Teams that cannot let a plugin run shell commands should stop here; that is a policy gate, not a window-size problem.

Watch out — It installed on a fresh profile and the harness registered it. We did not measure compression ratio, month-long sessions, or the stated 95–97% prefix-cache hit rate. README budgets ≤2% for compression itself and names /acp and /acp-cache when cache health falls.

The verdict — I would rather hit the wall once, then enable it, than spend a working session proving out a compressor this run never benchmarked.

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.Read the source
1Details

dscode

qiz029

998

A DeepSeek coding agent harness: persistent shell, Ultra subagents, auto approval, Chrome MCP and session telemetry

Did not install when we ran it

GitHub sourceJavaScript12d ago

AI review

dscode

What it is — A DeepSeek terminal coding agent with a persistent shell, file edits, and sessions on the same machine that can hand off work and review diffs.

Who it is for — You are on macOS or Linux, driving DeepSeek against a repo with builds and tests running, and you juggle more than one change set at a time. Skip it if you only want a small plugin inside a DSH profile you already run, not a replacement terminal agent.

Watch out — After a completed install, DSH did not register it into the profile, so it is not available as a plugin. You must supply an API key or token. It will run shell commands as part of the coding loop.

The verdict — Leave a working DSH install untouched. Come back only if profile registration starts succeeding, not because the feature table got longer.

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.Read the source
2Source

dsh-synapse

liangmianya

518

Visual, non-linear conversation workspace for DeepSeek Harness — sessions, follow-ups and branches become a browsable conversation map.

Installed cleanly when we ran it

npm packageJavaScript1mo ago

AI review

dsh-synapse

What it is — dsh-synapse turns DSH sessions, follow-ups and branches into a browsable conversation map.

Who it is for — If you use DeepSeek Harness in the web profile to handle multi-turn queries and branching discussions, this plugin helps manage the context through the map. Users who prefer simple linear conversations can continue using the native DSH dialog interface.

Watch out — It requires DeepSeek Harness >= 0.1.7-rc.2, Node.js >= 22.19.0 and the web profile. In the sandbox test, it installed successfully in a new profile and was registered by Harness. No obvious issues were found; the map data is stored in a separate directory, does not delete DSH native sessions, and does not modify core interfaces like prompts or model requests.

The verdict — If I were the user, I would install it because it supports bidirectional switching between the map and native dialog while preserving native sessions as the sole truth source, which benefits complex conversation management.

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.Read the source
Details

dsh-rewind

SiriLee

241

Conversation rewind: one click back to any earlier user message, in the same window — no new branch, no leftover copy; the target message is refilled into the composer, with optional workspace-file restore — the full Claude Code /rewind semantics.

Installed cleanly when we ran it

npm packageTypeScript3d ago

AI review

dsh-rewind

What it is — dsh-rewind plugin allows DeepSeek Harness users to rewind conversation in-place to any user message in the same session window, with optional file restore.

Who it is for — In DeepSeek Harness multi-turn agent task debugging that requires adjusting conversation context, it is suitable to install dsh-rewind. Users who only do plain text dialogue without needing file restore can consider other plugins.

Watch out — It requires installing the v0.9.x version of dsh-rewind on DSH 0.1.2-rc.1 or later, and running /dsh-rewind-fix to update old session rewind markers. Sandbox test passed: installed in a fresh profile and registered by harness. No obvious issues found.

The verdict — If rewind in-place plus file restore is needed, install it; otherwise skip, as fork-branch already meets basic needs.

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.Read the source
Source
238

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

npm packageJavaScript23d ago

AI review

dsh-chat-import

What it is — Turns chats from Claude Code, Cursor, ChatGPT and other agents into resumable DeepSeek Harness sessions, and can send them back to Claude Code.

Who it is for — You have a half-finished refactor sitting in Cursor or Claude Code and need that thread alive inside DeepSeek Harness instead of re-briefing the work. If each task starts from a spec and a clean session, this plugin has nothing to attach to.

Watch out — Install succeeded on a blank profile and the harness registered it. The plugin executes shell commands; that is a yes-or-no you decide up front. Import fidelity was not re-tested here.

The verdict — Leave it off the default profile; enable it only where threads are actually being moved.

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.Read the source
1Details