Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
Aegis provides a framework for making AI coding agents safer and more structured during long-term tasks. It introduces specialized workflows for dispatching parallel agents and pressure-testing high-complexity feature designs before implementation.
The system focuses on codebase health through anti-entropy governance, helping developers identify opportunities to retire legacy logic and resolve schema boundaries while requiring explicit confirmation for destructive changes.
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Follow the documented setup, then try a first task.
Agent-assisted global Aegis installation
Installs: Full Aegis Method Pack installed globally for the agent's detected host · AI coding agent
Before you start
An AI coding agent capable of identifying its host and following the repository's host guide
Python available as `python` for the documented doctor verification
In an AI coding agent session—not a terminal—send the following author-provided prompt. Keep its placeholders for the agent to resolve: `<profile>` is the selected DeepSeek Harness profile, `<aegis-method-pack-root>` is the installed Aegis method-pack root, `<path>` is a separate skill-discovery directory when applicable, and `<prefix>` is the host guide's required skill-directory prefix when applicable.
Read https://github.com/GanyuanRan/Aegis, identify my current AI coding host, and install Aegis globally using the correct host guide. If the host is the official DeepSeek Harness (`dsh`), treat global/minimal installation as native profile-plugin installation with `dsh plugin --profile <profile> add "git+https://github.com/GanyuanRan/Aegis.git"`; do not silently substitute the direct-child compatibility path unless the plugin manager is unavailable and I explicitly approve compatibility mode. Restart or reload the host if needed, then run complete-install verification from the installed Aegis method-pack root. Do not run the doctor command from the target project directory. First locate `<aegis-method-pack-root>`, then run `cd <aegis-method-pack-root> && python scripts/aegis-doctor.py --write-config --json`. Treat the install as complete only if the JSON includes `"ok": true`, `"workspaceSupport": "available"`, and `"configStatus": "configured"`; if the host uses a separate skill discovery directory, also verify it with `--discovery-root <path>`; if the host guide declares a skill directory name prefix, also pass `--discovery-name-prefix <prefix>`. Also complete the selected host guide's native activation and automatic-entry checks; file discovery or a generic doctor result alone is not sufficient when the host provides a plugin, hook, or session-start bootstrap contract.
Use the brainstorming skill to clarify this feature idea: [FEATURE IDEA]. Review the relevant context in [PROJECT PATH OR DOCUMENTS], ask one clarifying question at a time, and then propose 2–3 approaches with trade-offs and a recommendation. Present only the first compact design section for review; do not implement anything.
Use the goal-framing skill to frame only this task: [TASK DESCRIPTION]. Produce a short TaskIntentDraft covering the requested outcome, goal, success evidence, stop condition, non-goals, constraints, scope, risk hints, route, and next action. Do not execute, implement, or write a plan yet.
Use the first-principles-review skill to review this decision or proposed approach: [DECISION OR PLAN]. Consider these constraints: [CONSTRAINTS]. Give a lightweight review that identifies the governing first principle, any assumption that should be dropped, the smallest sufficient path, and any owner or retirement falsifier that could change the direction. Keep it advisory and do not implement changes.
Claude
Codex
Gemini CLI
OpenClaw
Copilot
OpenCode
Hermes
Antigravity
Grok
Kimi Code
DeepSeek
ZCode