aegis

Featured

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

plugin 536 stars 28 forks Updated today MIT

Install

Plugins install via a marketplace, in two steps.

This plugin isn't listed in a marketplace we've indexed. Install it directly from its GitHub repository — the README has the setup steps.

View on GitHub

Bundles

Everything this plugin ships — skills, agents, commands, hooks, and MCP servers it bundles.

Skills (22)

AI & Automation Solid

anti-entropy-governance

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.

536 Updated today
GanyuanRan
AI & Automation Solid

brainstorming

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

536 Updated today
GanyuanRan
DevOps & Infrastructure Solid

communicating-concisely

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

536 Updated today
GanyuanRan
AI & Automation Solid

dispatching-parallel-agents

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

536 Updated today
GanyuanRan
AI & Automation Solid

establishing-project-context

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.

536 Updated today
GanyuanRan
Code & Development Solid

executing-plans

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

536 Updated today
GanyuanRan
Code & Development Solid

finishing-a-development-branch

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

536 Updated today
GanyuanRan
Code & Development Solid

first-principles-review

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.

536 Updated today
GanyuanRan
AI & Automation Solid

goal-framing

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.

536 Updated today
GanyuanRan
AI & Automation Solid

long-task-continuation

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

536 Updated today
GanyuanRan
Code & Development Solid

receiving-code-review

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

536 Updated today
GanyuanRan
DevOps & Infrastructure Solid

recording-architecture-decisions

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.

536 Updated today
GanyuanRan
Show all 22 bundled skills
Code & Development Solid

requesting-code-review

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.

536 Updated today
GanyuanRan
AI & Automation Solid

subagent-driven-development

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

536 Updated today
GanyuanRan
Code & Development Solid

systematic-debugging

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

536 Updated today
GanyuanRan
Testing & QA Solid

test-driven-development

Use when implementing any feature or bugfix, before writing implementation code

536 Updated today
GanyuanRan
AI & Automation Solid

update-aegis

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.

536 Updated today
GanyuanRan
AI & Automation Solid

using-aegis

Use when starting a turn or checking Aegis skill routing.

536 Updated today
GanyuanRan
Code & Development Solid

using-git-worktrees

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

536 Updated today
GanyuanRan
Code & Development Solid

verification-before-completion

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

536 Updated today
GanyuanRan
AI & Automation Solid

writing-plans

Use when you have a spec or requirements for a multi-step task, before touching code

536 Updated today
GanyuanRan
AI & Automation Solid

writing-skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment

536 Updated today
GanyuanRan

Agents (1)

code-reviewer.md

Commands (3)

brainstorm.md execute-plan.md write-plan.md

Hooks (5)

copilot-session-start.ps1 hooks-cursor.json hooks.json run-hook.cmd session-start

Quality Score: 89/100

Stars 20%
91
Recency 20%
100
Manifest 20%
100
Documentation 15%
0
Issue Health 10%
80
License 10%
100
Description 5%
100

Details

Author
GanyuanRan
Repository
GanyuanRan/Aegis
Created
1 months ago
Last Updated
today
Language
Shell
License
MIT