A collection of coding-agent skills covering test-driven development, debugging, collaboration, and common engineering workflows. Test-driven development means writing a failing test before the code that makes it pass.

Use it for workflows such as writing tests first, investigating failures, coordinating independent work, and applying other included engineering practices.

It gives an agent established methods for handling development tasks instead of relying on an ad hoc process.

Aegis — Plugin for Claude Code by GanyuanRan: A collection of coding-agent skills covering test-driven development, debugging…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add GanyuanRan/Aegis

agentmods

npx agentmods add plugins/ganyuanran/aegis/aegis

Clone the repo

git clone --depth 1 https://github.com/GanyuanRan/Aegis

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/ganyuanran/aegis/aegis.svg)](https://agentmods.dev/plugins/ganyuanran/aegis/aegis)

Your own site

<a href="https://agentmods.dev/plugins/ganyuanran/aegis/aegis"><img src="https://agentmods.dev/badge/plugins/ganyuanran/aegis/aegis.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 22 skills, 3 commands, 1 hook cost 888 tokens a session between them.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

Aegis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude-plugin/plugin.json · 20 lines

What it actually says

{
  "name": "aegis",
  "description": "Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques",
  "version": "2.9.1",
  "author": {
    "name": "Aegis Maintainers"
  },
  "homepage": "https://github.com/GanyuanRan/Aegis",
  "repository": "https://github.com/GanyuanRan/Aegis",
  "license": "MIT",
  "keywords": [
    "skills",
    "tdd",
    "debugging",
    "collaboration",
    "best-practices",
    "workflows"
  ]
}

Contents

What it installs

The manifest is a name and a version. 22 skills, 3 commands, 1 hook travel with it, and installing the plugin installs all of them — 888 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

marketplace.json 445 B

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

3d ago First seen · 20 lines scan A fa977f515beb

Subscribe to this mod's changes

Aegis is a plugin published in the GitHub repository GanyuanRan/Aegis (1,154 stars, last pushed 5d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Debugging TDD Testing agent-skills ai-agents ai-coding architecture-driven-development claude-code codex

superpowers-zh

AI 编程超能力中文增强版：20 个 skills（14 翻译 + 4 中国原创 + 2 上游历史保留），支持 Claude Code / Hermes Agent / Cursor / Claw Code / Qoder 等 23 款工具.

jnMetaCode/superpowers-zh · not measured

spec-superflow

Spec-first workflow: integrates OpenSpec planning engine + Superpowers execution discipline. 9 collaborative skills with embedded TDD, SDD, code review, debugging, and delta spec sync.

MageByte-Zero/spec-superflow · not measured

zuvo

Multi-agent skill ecosystem for structured software development. 57 skills and 26 specialized agents with quality gates, code exploration, and evidence-based review.

greglas75/zuvo · not measured

pdlc

Turn AI software engineering into an auditable, on-disk state machine. A staged PDLC workflow (PRD, design, TDD, implement, review, ship, retro) enforces hard contracts — artifacts on disk, per-feature state machine, tests-before-code, objective checks from real command exit codes, single-shot auto-repair — so AI work.

kanfu-panda/pdlc-skills · not measured

shipyard

Turn your idea into working code — Shipyard runs Claude Code through a spec-driven agile sprint lifecycle: discuss features, plan sprints, build with TDD, review, and ship.

Acendas/shipyard · not measured

devflow

Full-lifecycle AI development workflow — fuses grill-with-docs (Matt Pocock) + OpenSpec (Fission-AI) + superpowers (obra) into one disciplined pipeline. Three modes: Design (quick-grill → spec-lite), Build (grill → spec → plan → isolate → enhanced-apply → review → archive), Fix (diagnose → apply → verify → archive).

AppleCG/devflow · not measured