withkynam/vibecode-pro-max-kit
Coding · tested 2026-09-30 · by the Hlido desk, not the vendor
In short: Well-adopted spec-driven coding harness aimed at context rot — strong traction and agent-consumable, but install/usage docs are thin.
9 PASS · 1 FAIL of 10 public-surface claims
Quick answer
withkynam/vibecode-pro-max-kit scores 82/100 (STEADY) on Hlido’s independent, hands-on test (reviewed 2026-09-30). STEADY (82) on solid repo health and real traction, with the agent-consumable pass rewarded by the track. Pricing: Open source (free entry point documented).
vibecode-pro-max-kit is a spec-driven coding harness pitched at the 'your AI forgets' problem — self-improving context memory, a bundle of agents and skills, targeting Claude Code and Codex across any stack. The measured signals are healthy: 1,042 stars, 219 forks, MIT-licensed, releases present, CI in place, actively pushed, and it passes the agent-consumable check. The positioning — persistent context and spec-first workflow to stop 'context rot' — is a real pain point for anyone doing long agent-assisted builds, and the fact that it is consumable inside Claude Code and Codex fits the agent-to-agent thesis. The gap the engine flagged is worth taking seriously for a tool whose whole promise is smooth onboarding: no clear install/usage markers were found in the README, so despite the '30-second' framing the actual setup path is under-documented on the surface we read. Combined with the absence of a hands-on run, that means the memory and self-improvement claims are unverified. Strong momentum and a good idea; ask to see the setup docs before committing a team to it.
Why STEADY
STEADY (82) on solid repo health and real traction, with the agent-consumable pass rewarded by the track. Below VITAL because of the repo-surface ceiling and the missing install/usage documentation — the one failed checklist item, and a pointed one for a tool that sells fast onboarding.
Public-surface checklist
- PASS Repo reachable (required) — GH API 200 for withkynam/vibecode-pro-max-kit
- PASS Readme present (required) — README length 95623
- PASS License present (required) — MIT
- FAIL Install documented (required) — no install/usage markers
- PASS Active 12mo (required) — last push 25d ago
- PASS Releases present — latest v3.2.5
- PASS Community traction — 1042 stars
- PASS Ci or tests — 4 workflow file(s)
- PASS Recent commit 90d — last push 25d ago
- PASS Agent consumable — CLI install line in README
What we saw
1 screenshot captured by the Hlido engine during the reviewed run (run-1abc69e897b7a90d-github-com). Our own captures — not vendor marketing material.
What it does well
- Strong traction (1,042 stars, 219 forks) for a young harness
- Agent-consumable and explicitly targets Claude Code and Codex
- MIT-licensed with releases and CI present
- Addresses a real pain point — context persistence across long agent-assisted builds
What it fails at
- No clear install/usage markers found in the README — setup path under-documented despite the "30-second" claim
- Not hands-on tested: the context-memory and self-improvement claims are unverified
- Heavy marketing framing ("pro max", "GOAT") outruns the documented evidence
Best for
- Developers doing long agent-assisted builds who feel context rot acutely
- Claude Code / Codex users wanting a spec-first harness
- Teams willing to read the source to fill the documentation gaps
Not recommended for
- Buyers who need turnkey, well-documented onboarding today
- Anyone wanting verified proof of the memory claims before adopting
- Stacks outside the Claude Code / Codex orbit
Pricing & access
- ModelOpen source
- Free entry pointYes — a free tier or open-source edition is documented
Derived from Hlido-held evidence only (engine checklist + editorial text); quotes are verbatim from the scorecard; not vendor-supplied; re-derived daily. Verify current prices on the vendor's pricing page. Last verified 2026-07-16.
Related agents
Agent relevance
No programmatic surfaces
Agentic-Commerce Readiness 31/100 · SURFACE-ONLY
Independent readiness for agent delegation & transaction. How it’s scored · check live
Consumed as a harness of agents and skills inside Claude Code or Codex. Agent-consumable, but the thin install documentation raises the wiring cost.
Agent-friendly score: 6/10
Score over time
The longitudinal record — every point is the score as published on that date. Raw series.
