Skip to main content
ClaudeWave

Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.

Subagents506 stars27 forksShellMITUpdated yesterday
ClaudeWave Trust Score
97/100
Verified
Passed
  • Open-source license (MIT)
  • Actively maintained (<30d)
  • Healthy fork ratio
  • Clear description
  • Topics declared
Last scanned: 6/11/2026
Install as a Claude Code subagent
Method: Clone
Terminal
git clone https://github.com/GanyuanRan/Aegis && cp Aegis/*.md ~/.claude/agents/
1. Clone the repository and copy the agent .md definitions into ~/.claude/agents (or .claude/agents inside a project).
2. Start a new Claude Code session to load the agents.
3. Delegate work to them with the Task/Agent tool or by name.

24 items in this repository

|

Install
brainstormSlash Command

Deprecated - use the aegis:brainstorming skill instead

Install
execute-planSlash Command

Deprecated - use the aegis:executing-plans skill instead

Install
write-planSlash Command

Deprecated - use the aegis:writing-plans skill instead

Install

Use when retiring old logic, collapsing duplicate owners, removing fallbacks, or touching schema, persistence, or source-of-truth boundaries while deciding whether to delete old paths, retain compatibility, or stop for confirmation.

Install

Use when defining new features, product behavior, UI/component design, architecture choices, contract changes, or ambiguous medium/high-complexity work before implementation.

Install

Use when the user asks for caveman mode, fewer tokens, brief responses, compressed communication, or otherwise explicitly requests a much shorter answer.

Install

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Install

Use when entering a project for the first time, or when the user asks to establish shared language, define domain terms, or create a project glossary.

Install

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Install

Use when implementation is complete, verification has passed, and the user needs to choose merge, PR, branch cleanup, or follow-up integration handling.

Install

Use when the user explicitly asks for first principles, first-principles review, Occam's razor, or when a complex decision has ambiguous goals, competing constraints, repeated fixes, fallback growth, duplicate owners, or architecture/product direction risk.

Install

Use when the user explicitly sets an Aegis goal with /aegis-goal, Aegis goal:, or asks to define goal, success evidence, stop condition, or task boundaries before work.

Install

Use when a task is multi-step, may span context resets or sessions, uses subagents, or risks losing state before completion.

Install

Use when receiving code review feedback before implementing suggestions, especially when feedback is unclear, risky, disputed, or technically questionable.

Install

Use when the user asks to create, write, update, amend, supersede, or evaluate an ADR, architecture decision record, durable architecture decision, decision log, or baseline sync after architecture-changing work.

Install

Use when explicitly requesting an independent code review, after subagent-driven implementation slices, before merging high-risk work, or when verification finds evidence, baseline, architecture, compatibility, or retirement uncertainty that needs reviewer scrutiny.

Install

Use when executing implementation plans with independent tasks in the current session

Install

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Install

Use when strict TDD is explicitly requested, or when an approved atomic implementation task has already chosen TDD Route strict.

Install

Use when the user says `aegis:update`, asks to update or upgrade an installed Aegis method-pack, wants the latest Aegis version, or asks whether Aegis is current on this host.

Install

Use when starting a turn or checking Aegis skill routing.

Install

Use when starting feature work that needs isolation from the current workspace, or when an implementation plan should run outside the active working tree.

Install

Use when about to claim work is complete, fixed, passing, verified, release-ready, or ready to commit, merge, publish, or hand off.

Install
Use cases

Subagents overview

README preview not available. Visit the repo on GitHub for full documentation.
addagent-skillsai-agentsai-codingarchitecture-driven-developmentbaseline-firstclaude-codecodexcoding-agentsevidence-drivenfirst-principlesopencodesoftware-architecturesuperpowerstdd

What people ask about Aegis

What is GanyuanRan/Aegis?

+

GanyuanRan/Aegis is subagents for the Claude AI ecosystem. Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks. It has 506 GitHub stars and was last updated yesterday.

How do I install Aegis?

+

You can install Aegis by cloning the repository (https://github.com/GanyuanRan/Aegis) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.

Is GanyuanRan/Aegis safe to use?

+

Our security agent has analyzed GanyuanRan/Aegis and assigned a Trust Score of 97/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.

Who maintains GanyuanRan/Aegis?

+

GanyuanRan/Aegis is maintained by GanyuanRan. The last recorded GitHub activity is from yesterday, with 0 open issues.

Are there alternatives to Aegis?

+

Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.

Deploy Aegis to your cloud

Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.

Maintain this repo? Add a badge to your README

Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.

Featured on ClaudeWave: GanyuanRan/Aegis
[![Featured on ClaudeWave](https://claudewave.com/api/badge/ganyuanran-aegis)](https://claudewave.com/repo/ganyuanran-aegis)
<a href="https://claudewave.com/repo/ganyuanran-aegis"><img src="https://claudewave.com/api/badge/ganyuanran-aegis" alt="Featured on ClaudeWave: GanyuanRan/Aegis" width="320" height="64" /></a>

More Subagents