Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for AI-coding power users, agent developers, automation builders, engineering teams, DevOps engineers, SREs, engineering managers, AI-curious readers, founder-CTOs, technical writers, and any developer who runs Claude Code / Cursor / Codex / Gemini CLI on a long-running coding workflow and wants a curated, battle-tested skill library + harness + adversarial verifier + Plan-Act-Verify loop r
Who should use it
Who should skip it
Skip Archive228/loopkit if the source repository or demo is inactive, unmaintained, or no longer matches the description shown here.
About this signal
Archive228/loopkit is tracked by RepoRadar as a drop-in .claude/ harness + 33 ba in the Claude Code / Coding Agent Skills section. It was first seen on 2026-07-06 and last updated on 2026-07-06. The current verdict is 'try now' with a Silver tier and easy setup difficulty. Across RepoRadar's eight signals, Archive228/loopkit is strongest on workflow potential (9.4) and setup ease (8.8) and weakest on maturity (5.8) — 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 Archive228/loopkit a composite score of 7.9 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 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 375* / 253KB TypeScript codebase is recent (created 2026-06-30; 6 days before this cycle) and the community is mid-sized -- treat the first evaluation cycle as a smoke test (npx claude-loopkit init in a target repo + commit the .claude/ + skills/ + .mcp.json + MEMORY.md + run.sh files + ask the agent to debug a failing test + ask the agent to refactor a hot path + ask the agent to review a PR) before relying on the 33 skills in production; the .claude/CLAUDE.md (60-line standing context) is the durable opinionated layer -- audit the standing context before deploying to a multi-tenant environment to confirm the opinionated default matches the team's coding style; the .claude/settings.json permission allowlist + format-on-write hook is the right default but a team SHOULD audit the allowlist before going live (the allowlist determines which tools the agent can invoke without per-call approval).