dsh-egm

🐘 dsh-egm 🐟

English  ·  简体中文

Design with an elephant. Review with a goldfish.

Install  · 

Quickstart  · 

How it works  · 

The plugin  · 

Skills  · 

Example run  · 

Feedback

Google's Elephant-Goldfish Model, adapted for DeepSeek Harness.

Meet the Elephant 🐘

The Elephant is your long-running design partner.

It explores your project, reads the relevant code, asks questions, and helps you work through alternatives. It keeps track of the decisions you've made and the reasons behind them. Together, you develop a design document.

But the Elephant has a problem. It remembers too much.

After hours of discussion, it understands what you meant, even when you haven't written it down. Ask the Elephant whether the design makes sense, and it might unconsciously fill in the gaps from your earlier conversation.

That's dangerous, because whoever implements the design next won't necessarily have that context.

We need someone who doesn't remember.

Meet the Goldfish 🐟

The Goldfish starts fresh.

It hasn't participated in your design discussions. It doesn't know why you chose a particular architecture or which requirements you explained but forgot to write down. It receives a self-contained review prompt, the design, and the reference material it needs. It can read and search permitted project files, but it doesn't inherit the Elephant's conversation.

Then it tries to understand what you've written.

Can it figure out how the system is supposed to work? Are the requirements unambiguous? Are failure cases accounted for? Do the interfaces fit together? And, most importantly, could someone build this correctly without having been part of the original conversation?

When the Goldfish discovers a problem, the Elephant helps you address it. You revise the document, review it again, and decide when it's ready.

The result isn't just a specification. It's project knowledge that can survive the conversation that created it.

Why bother?

AI coding assistants have three recurring failure modes:

1. Forget. Important decisions disappear when a conversation is compacted or restarted.

2. Assume. An assistant confidently implements requirements nobody actually agreed on.

3. Agree. An assistant reviewing its own design can quietly carry the same unwritten assumptions into the review.

The [Elephant-Goldfish Model](https://github.com/google/elephant-goldfish-model) (EGM) separates the context-rich design conversation from independent, fresh-context criticism. dsh-egm brings that workflow to [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) as a native plugin.

It's useful when a feature, migration, or architectural change needs decisions before code. For a small, well-understood bug fix, your normal coding workflow is probably enough.

Install

You'll need:

• DeepSeek Harness 0.2.x, compatible with the package's declared range >=0.2.1-rc.5 <0.3.0.
• Node.js 22 or 24 (>=22 <25; CI tests Node 22 and 24). If you're using the DSH 0.2.2 alpha line, its own requirement is Node 24.9 or newer.

Install the plugin into your Harness profile. The example uses web; substitute the profile you actually use.

dsh plugin --profile web add dsh-egm

Restart Harness, then check Settings → Plugins to confirm it's enabled.

The bundle declares the read-only egm-reviewer preset, but it does not create the host's agent-preset service. egm_reviewer needs a profile that composes an agentPresets registry resolving a valid default preset, plus an in-process spawn subagent provider. Harness web profiles already compose both. For a profile without a registry (for example headless), the package ships an opt-in patch: add --patch /adapters/dsh/agent-presets.patch.yml when starting the profile. Without a registry egm_reviewer fails closed (the agent-presets service is not composed); the [host guide](docs/dsh.md#host-prerequisites-and-current-limit) lists the exact refusals and the observed effect of applying the patch to a profile that already has a registry. The package does not compose the registry automatically.

For local development, you can install from a checkout instead:

dsh plugin --profile web add /path/to/dsh-egm

Quickstart

Copy each slash command below into the Harness chat.

Imagine you're adding webhook delivery to an application. Before writing code, you need answers to questions like: What happens if delivery fails? What if the same event arrives twice?

1. Explore the idea.

/egm-brainstorm Add webhook delivery to this application.

The Elephant helps you explore requirements, alternatives, and trade-offs. The brainstorming workflow can bring in fresh reviewers to challenge the proposal. You and the Elephant settle on a direction and record it in a concept brief.

2. Draft the design.

/egm-draft

The Elephant develops a specification section by section, asking for your decisions rather than silently filling in the blanks. The working draft is design_draft.md in your project working directory (or the EGM artifact directory). When you finalize it, the skill asks where to save and writes the final design as .md; the default directory is docs/designs/, for example docs/designs/webhook-delivery.md.

3. Send in the Goldfish.