#149149th of 324 in Skills, plugins and prompts
aegis
Skill pack that makes AI coding agents plan, verify and report evidence
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 1.4k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Python
1 on 1 May 20261,408 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Aegis is a method pack of SKILL.md-style skills that coding agents load to align with a project's baseline before editing and to attach verification evidence to completion claims. It installs through an agent prompt and a Python doctor script (scripts/aegis-doctor.py) on hosts such as Codex, OpenCode and Claude Code. It also provides optional TDD routing and an update command.
Who it is for: Developers using AI coding agents who want fewer reworks and proof of completion
Strengths
- Works across many hosts: Codex, OpenCode, Claude Code, Kimi Code CLI, Copilot and others
- Publishes an A/B benchmark: contract pass rate 61.67% to 93.33% over 120 runs
- TDD mode is off by default and can be set to auto via a doctor command
- Install is checked by a doctor script that outputs JSON with ok and configStatus
Weaknesses
- Benchmark covers one model setup (gpt-5.6-sol, xhigh); review was not independent human review
- Only Codex and OpenCode have fresh host evidence; other hosts await release-level smoke tests
- Skill triggering stays host-controlled and may need trigger-chain diagnosis
- Not a runtime or gate: completion authority stays with the user and project rules
What it needs
- no GPU
- Needs Python, AI coding host (Codex, OpenCode, Claude Code or similar)
Quick answers
Is aegis open source?
Yes. Its code is on GitHub under the MIT license.
Also in Skills, plugins and prompts
See all 324| Rank | Project | Score |
|---|---|---|
| 1 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 96 out of 100 |
| 2 | skillsAgent skills for planning, TDD, debugging and code review | 95 out of 100 |
| 3 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 95 out of 100 |
| #4 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 95 out of 100 |
| #5 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |