Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for AI agent developers, researchers, paper writers, and power users who use Claude Code + Codex + Cursor (or any combination) and want one `AGENTS.md` that drives all three, with cross-machine sync via a 4-method auth chain (SSH agent → `gh` CLI → `GITHUB_TOKEN` → anonymous), per-project overrides via `agent-config.yaml`, and a `agent-pack` reference repo (fork-and-replace) for authoring y
Who should use it
Who should skip it
Skip yzhao062/anywhere-agents unless the captured evidence suggests it solves a problem you are actively working on.
About this signal
yzhao062/anywhere-agents is tracked by RepoRadar as a agent config composer in the AI Coding section. It was first seen on 2026-07-03 and last updated on 2026-07-03. The current verdict is 'try now' with a Gold tier and easy setup difficulty. Across RepoRadar's eight signals, yzhao062/anywhere-agents is strongest on workflow potential (9.1) and practical usefulness (9.0) and weakest on maturity (6.3) — 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 yzhao062/anywhere-agents a composite score of 8.0 out of 10, placing it in the Gold 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 1.0 and never affects the composite score or tier. The risk label of 'low' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
The destructive-command PreToolUse guard blocks `rm -rf /`, disk-wipe, and force-push — review the guard.py rule list before promoting to multi-user deployment, and add legitimate-but-blocked commands to the allowlist (e.g. `rm -rf build/` in a cleanable workspace) per project; the guard is the right default but is not a substitute for sandboxed execution environments; The agent-style AI-tell guard blocks writes that contain ~45 banned words on `.md` / `.tex` / `.rst` — the guard is intentionally aggressive and will block legitimate writes that happen to use one of the banned words; review the `agent-style` rule list in the bundled-defaults and adjust per project (the README documents the per-pack policy table: passive / auto / prompt); The /implement-review skill hands the staged diff to a second reviewer (Codex / GitHub Copilot / headless Claude Code) — the second reviewer consumes tokens and incurs per-call cost; configure the reviewer to a model that matches the cost budget for the project (small models for trivial diffs, larger models for risky ones), and pin the reviewer in `agent-config.yaml` so it does not silently swap.