DSH Marketplace

Aegis

GanyuanRan/Aegis

Software-engineering method pack for coding agents, with skills for baseline-first planning, systematic debugging, prompt hygiene, verification before completion, and repair/retirement tracking.

1,35688PythonMITSource

Install

Add Aegis 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 11d 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 Aegis

  • Source of record: GanyuanRan/Aegis — present in the community registry that DSH's own plugin market installs from.
  • Licensed under MIT.

Security

What installing Aegis runs

Build scripts

No build script was blocked in our run.

Source: our sandbox install on DeepSeek Harness 0.2.2-rc.1, 11d 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

shell commands (bash, exec, spawn …)

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 — A method pack that makes a coding agent plan off the live project baseline, debug in a structured way, attach evidence before it may finish, and keep a ledger of repairs and retirements.

Who it is for — You run a DeepSeek Harness agent on a repo that already has owners and contracts, and it still edits first, then reports finish with no covered scope. People who only ask it to explain code or draft comments, and never let it change logic or run checks, have nowhere to attach this.

Watch out — A clean profile install worked and the harness registered it. It runs shell commands. The README’s contract pass rate move from 61.67% to 93.33% and unsafe-outcome drop from 13.33% to 0% is frozen A/B evidence from Aegis 2.7.6 (2026-08-11), not a score for this release.

The verdict — I’d add it for the completion gate, not for another wrap-up writer.

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 Aegis does

Layered blocks flow through checks into a verified form, with discarded fragments separated.

Aegis is a DeepSeek Harness plugin that gives coding agents a software-engineering method pack for planning, debugging, prompt hygiene, verification, and repair or retirement tracking.

It projects these methods into a skill-aware host rather than adding a separate coding tool. Before editing, the agent is expected to establish the project's real baseline, including owners, contracts, and boundaries. Before declaring completion, it should produce fresh verification evidence, identify the covered scope, and record residual risk. The pack also keeps retired fallbacks and old paths tied to a retirement trigger instead of leaving them as untracked technical debt. Simple tasks can remain on a fast path; the documented method is intended to add ceremony when the task needs it.

Aegis is aimed at coding-agent workflows where changes need explicit planning and evidence. It is less suitable when the host cannot load skills or when its existing workflow already provides the same planning and verification discipline. The README documents host-specific activation requirements, including native plugin installation for DSH and additional discovery checks where a host uses a separate skill directory.

The detected terminal surface matters: the plugin's verification flow runs commands such as python scripts/aegis-doctor.py --write-config --json from the method-pack root and may pass discovery-root and name-prefix options. That gives the agent a terminal-based path to inspect installation and workspace support, with the agent's available permissions.

Aegis documentation

How it behaves

Aegis is presented as a method pack projected into a skill-aware coding host. Its documented practices cover baseline-first planning, systematic debugging, prompt hygiene, verification before completion, and two-track repair or retirement tracking. The baseline is expected to include project owners, contracts, and boundaries. Completion evidence should be fresh, state the covered scope, and identify residual risk. Trivial requests can remain on the fast path.

Installation verification

The README requires verification from the installed method-pack root, not from the target project directory. Locate <aegis-method-pack-root> first, then run:

cd <aegis-method-pack-root> && python scripts/aegis-doctor.py --write-config --json

The installation is considered complete only when the JSON contains all of the following:

Field Required value
ok true
workspaceSupport available
configStatus configured

The --write-config option writes the configuration used by the doctor flow, while --json requests machine-readable output.

Host activation

For the official DeepSeek Harness (dsh), the README specifies native profile-plugin installation with dsh plugin --profile <profile> add github:GanyuanRan/Aegis. The direct-child compatibility path should not be substituted unless the plugin manager is unavailable and compatibility mode is explicitly approved. Host activation and automatic-entry checks must also be completed; file discovery or a generic doctor result is not sufficient when the host defines a plugin, hook, or session-start bootstrap contract.

Discovery options

When a host uses a separate skill discovery directory, repeat verification with --discovery-root <path>. If its host guide defines a skill-directory name prefix, also pass --discovery-name-prefix <prefix>. The README names Codex, Claude Code, OpenCode, and Kimi as other skill-aware hosts.

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 Aegis

dsh-skill-explorer

zhu1090093659

10k

Skill center for the dsh web GUI: browse all loaded skills grouped by source, enable or disable model invocation, create new skills, and delete into a recoverable trash.

Installed cleanly when we ran it

npm packageTypeScript2d ago

AI review

dsh-skill-explorer

What it is — A DSH Web GUI page that lists loaded skills by origin, with invocation toggles, creation, and a trash you can restore from.

Who it is for — You run agents in the DSH Web GUI with skills piled in from several origins, and the model keeps hitting ones you wanted left idle. Anyone who only edits skill files in a terminal and never opens the Web GUI has no use for this panel.

Watch out — On a fresh profile it installed and the harness registered it. No sharp edges showed up in that run.

The verdict — A single setup pass on invocation flags does not earn a plugin slot from me; I add it only when I keep turning skills on and off.

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

Answers a question with a one-page visual HTML explainer: the model writes a short Markdown draft and the bundled `am` CLI builds the page, with flow, sequence, tree, timeline and ER diagrams, tables and callouts.

Installed cleanly when we ran it

GitHub sourceJavaScriptyesterday

AI review

answer-me-with-html

What it is — Questions come back as one HTML page: the model stops at a short Markdown draft, and the bundled am CLI draws layout plus flow, sequence, tree, timeline and ER diagrams, tables and callouts.

Who it is for — You are in DeepSeek Harness unpacking a handshake, a repo module map, or Redis versus Memcached, and a terminal transcript cannot show the structure. Skip it if the agent only patches code and runs tests, or if answers already land in a docs repo you maintain—the extra file has no place in that path.

Watch out — In a fresh profile it installed and the harness registered it. Node.js 20 or newer is required, and the bundled am CLI is invoked through the shell. Their Claude Sonnet 5.5 numbers on a plain Claude Code setup: model-written tokens about 4,893 versus 612, 31 s versus 12 s, bill down only about 15% because each turn still reads the system prompt, the question and the thread.

The verdict — I would enable it on a profile reserved for explainers I will send or reopen, and leave it off sessions that die in the terminal.

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

skillhub

iflytek

5.3k

Browse and search a SkillHub registry and manage local skill installation, updates, and removal inside DeepSeek Harness. Targets DSH 0.2.0-rc.2 and 0.2.1-rc.2; not yet compatible with 0.2.1-rc.3.

No one-line install — this plugin lives inside a larger repository and publishes no npm package.

GitHub sourceJava25d ago

AI review

skillhub

What it is — A DeepSeek Harness plugin that queries a SkillHub registry and installs, updates, or removes skills on the local machine.

Who it is for — You do agent work inside DeepSeek Harness while the skills your team actually reuses already live in a SkillHub you can reach, and you are still jumping out to fetch packages. If skills move as git repos or shared folders and your day is not spent in DSH, skip this plugin.

Watch out — It is not published as a one-command package; you have to wire it from a repository subdirectory. It runs shell commands and expects an API key or token. It targets DSH 0.2.0-rc.2 and 0.2.1-rc.2 and is not compatible with 0.2.1-rc.3.

The verdict — This is not a reason to introduce SkillHub; I would only attach it after a registry is already how skills get distributed.

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

dashi-taskboard

chuspeeism

3.4k

现代化可灵活嵌入的任务面板,支持 Codex、DeepSeek Harness

Installed cleanly when we ran it

GitHub sourceJavaScript19d ago

AI review

dashi-taskboard

What it is — A local-first issue board whose HTTP API feeds both a browser UI and taskctl, with a CDP path into Codex.

Who it is for — You are cutting slices in the Codex desktop app and need the agent to inspect issues and move their status on a machine-local board. If DeepSeek Harness is your only surface and you expect a matching in-harness panel after install, skip it—the writeup never describes that UI, only Codex injection and desktop apps.

Watch out — On a clean profile it installed and the harness registered it. It runs shell commands and wants an API key or token; the service needs Node.js 22.5 or newer. The Codex launcher or injector has to stay running while the panel is used, and desktop builds add Rust 1.88 plus Xcode or Visual Studio Build Tools.

The verdict — I would keep it for the Skill’s last gate—done only after I accept—not because it registered.

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

vox-director

Alisa0808

2.5k

Turn one topic into a finished Vox-style paper-collage explainer/ad video — automated end to end on Atlas Cloud + ffmpeg. An agent skill.

Installed cleanly when we ran it

GitHub sourcePython1mo ago

AI review

vox-director

What it is — An agent skill that takes one topic through beat maps, collage posters, motion, voice-over, music and burned-in captions and writes a Vox paper-collage mp4 .

Who it is for — You are cutting explainer or ad shorts inside Claude Code or Codex from a topic line, a talking-head, or a product still, and you lack a skill that owns that collage path. Skip it if you only need to swap narration or BGM on an edit that already exists; this is not a detachable TTS plugin and it re-enters through beats.json .

Watch out — It calls Atlas Cloud for image, i2v , TTS and music, then shells out to local ffmpeg.You approve the beat map and pick a look by eye before the rest runs. Sandbox: it installed on a fresh profile and the harness registered it.

The verdict — I leave it registered and judge from the first posters; thin paper texture and I pull it rather than debug the video stage.

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
1Source
1.9k

Daily radar for new AI terms: names of new models, products and repos, caught on X, Hugging Face, GitHub and sitemaps before keyword tools list them.

Installed cleanly when we ran it

GitHub sourcePython20d ago

AI review

new-term-radar

What it is — Collects new AI model, product and repo names from X, Hugging Face, GitHub and sitemaps, ahead of keyword tools.

Who it is for — You are writing pages for an AI-tool site or picking the day's newsletter lead, and you need names that just surfaced. If your DeepSeek Harness work is code and agent wiring, this list has no downstream.

Watch out — It installed on a fresh profile and DeepSeek Harness registered it. X and new-site signals need an AIsa key and bill per run; Hugging Face, GitHub and sitemaps do not. It executes shell commands.

The verdict — I would keep it only as a daily report habit; a one-off name check is not worth a plugin slot.

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
1Source