Autonomous software factory: fetches tasks from GitHub/GitLab/Linear, implements them with an AI agent pipeline in a Docker sandbox, and opens draft PRs for human review.
This repository also configures its own agents. See what vanguard tells them →
Skill Claude CodeCodex
Use to minimize token use on long or repetitive agent work. Cut all prose to the bone — no preamble, no restating the task, no narrating steps, no closing summary. Spend tokens on the work, not on words.
Skill Claude CodeCodex
Use when reviewing a code change or diff for correctness, security, missing tests, and convention violations before opening or approving a PR. Review independently and adversarially, then fix high-confidence issues.
Skill Claude Code
Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports…
Skill Claude CodeCodex
Use after writing or modifying code to improve its clarity, reuse, simplicity, and efficiency without changing behavior. Not for finding correctness bugs — that is code review.
Skill Claude CodeCodex
Use when a task is under-specified and needs a written technical specification BEFORE any code is written or changed. This skill only researches and documents — it never edits source files. Do not invoke for implementing, reviewing, or simplifying existing code.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: