variant_b // terminal_editorial // animations: none

One CLI conducts three vendors. Gates make it safe.

agentflows fans tasks out to Kimi K3, MiniMax-M3, and claude workers under a single schema-validated contract. Everything below was measured in this repo on 2026-07-17 — this page is a spec sheet, not a pitch.

capability demos lab notes

metric	method	value
repo tests	`npm test` at audit time	100/100 pass
swarm audit	4 read-only K3 subagents, disjoint scopes	3 P0 · 8 P1 found
citation check	spot-verified against source	6/6 verified
caveman condensing	K3, verbose doc → 6 bullets	−46% words
caveman generation	K3, dense handoff prose	+11% (worse — generation stays normal)

Capabilities

4 entries · each runnable

review

Long-context code review

K3 first pass, evidence-backed findings; MiniMax-M3 cross-check verifies and hunts misses.

-> swarm

AgentSwarm exploration

Parallel read-only subagents on disjoint scopes; lead synthesizes one verified answer.

-> fallback

Quota-aware fallback

402 / entitlement classifies as quota; chain degrades Kimi → MiniMax-M3 unassisted.

-> site

Prompt-to-site

Static page concepts as safe, reviewable artifacts inside the lab boundary.

The loop

structural gates, not vibes

Downstream agents never spawn until the upstream gate clears. Rejections loop back with findings attached, then halt for a human. The same loop reviewed this page before you read it.

[dispatch] ──▶ [review: kimi-k3] ──▶ [crosscheck: minimax-m3] ──▶ [gate: pass]
                  │                        │                          │
                  │  one task contract     │  verify + hunt misses    │  severity-ranked
                  │  schema-validated out  │  corroborated > single   │  human approves
                  ▼                        ▼                          ▼
             findings.md              verified set               ship or halt

Run it

expected: halt at gate on fixture bug

$ shellread-only until approved

node bin/aflow.js workflow run top-review-lab --variant strict
# or the two-model corroboration loop:
aflow flow run crosscheck --diff HEAD~1 "review this change"

Boundaries

No credentials, transcripts, or session state in any demo page.
No mutation outside experiments/skills-workflows-hooks-lab/.
Static HTML/CSS only — no backend, no trackers, no animation budget.