Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for solo developers and small teams using Claude Code who want a structured, stage-gated AI dev-team workflow instead of an ad-hoc `claude` chat: a 19-person team organized by PRD → implementation → review → deploy → test → signoff, a 4-layer hook system that blocks risky actions before they happen, DoD checklists that the agents must satisfy, and a trilingual 中文 / English / 日本語 README; for
Who should use it
Who should skip it
Consider pcliangx/AppGenesisForge lower priority if you already have a working solution in this category.
About this signal
pcliangx/AppGenesisForge is tracked by RepoRadar as a claude code ai dev-team scaffold in the MIT Claude Code 19-person AI dev-team scaffold ( section. It was first seen on 2026-06-25 and last updated on 2026-06-25. The current verdict is 'try now' with a Silver tier and moderate setup difficulty. Across RepoRadar's eight signals, pcliangx/AppGenesisForge is strongest on workflow potential (8.9) and open-source/build quality (8.4) and weakest on setup ease (6.4) — a profile worth weighing against your own priorities. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.
How this item is evaluated
RepoRadar assigned pcliangx/AppGenesisForge a composite score of 7.8 out of 10, placing it in the Silver tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 240.0 and never affects the composite score or tier. The risk label of 'conditional' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
Risk explanation
**The 4-layer hook system blocks risky actions before they happen — read the hook layer before adopting.** The README points at `.claude/standards/security.md` for the hook definitions; users adopting the scaffold should read the hook layer first and confirm the blocking rules match their workflow (e.g. the hook system may block `rm -rf`, force-push, or other actions the user expects to be able to run manually), and the scaffold is conditional-rated for that reason — the user has to opt into the hook layer's blocking rules; **Trilingual README is honest about its primary audience.** The README opens with 简体中文 and ships English + 日本語 translations; the primary audience is the Chinese-speaking Claude Code community and the 微信小程序 track is a first-class supported track, so non-Chinese-speaking readers may find the trilingual README heavier than they need; the install path is language-neutral but the documentation examples skew to Chinese-language projects; **Three supported tracks, three explicit non-supported areas.** The README is explicit: AGF supports Web (React+FastAPI+Postgres), 微信小程序, and Apple native macOS+iOS; AGF does NOT support Android native, Windows / Linux desktop, or LLM training — users outside the three supported tracks should not adopt AGF as their primary scaffold.