- 01INSTALL PLAY
- 02GUIDE ONE RUN
- 03GET A REUSABLE PLAY
$ play
▸ what should your agent never solve twice?
› is my website ready to launch?
claude code › exploring · dns · tls · headers · metadata · lighthouse
@1dns✓records resolve
@2tls✓certificate valid
@3headers✗content-security-policy missing · corrected and retried
@4headers✓six checks pass
@5metadata✓title · description · og:image
@6lighthouse✓performance · accessibility · seo
the job worked. keep what made it work as a Play?▸ YES, SAVE THE PLAY
✓Play minted8 stepsread-onlydigest verified
- 01 · YOU ASK
- Is my website ready to launch?
- 02 · YOU GET
play.modiqo.ai/modiqo/[email protected]INSPECT ↗- 03 · NEXT RUN
- 8 known steps · read-only · same path every time
THE PROBLEM
Does this sound familiar?
01FLAKY The same request, run twice, takes two different paths.
02EXPENSIVE Every run pays for discovery again, and the bill changes each time.
03UNGOVERNED A rule for an agent is a post-it note. You cannot guarantee it holds.
04HARD TO SHARE Good work stays in the chat where it happened. Sales, marketing, and ops start from zero.
WHAT ROTE IS
Every call your agent makes is traced. The path that worked becomes a Play.
- the failed paths? dropped.
- only what worked is kept
- same method every time, fresh inputs each run, a fraction of the tokens
A Play is inspectable by design.
Move proven work beyond the frontier model.
- discover once, at frontier prices
- every repeat runs on a lower-cost model
- one URI your team and the community can run, inspect, improve
[.788] [.616] [.505] [.410]
[.400] [.805] [.265] [.273]
[.410] [.206] [.043] [.505]
[.273] [.505] [.765] [.665]
[.477] [.265] [.143] [.083]
[.087] [.043] [.095] [.900]
14,900 tokens · discoverymodiqo/hello 8 steps · read-only digest 3f9c1a… open modiqo/hello ↗
run 07 haiku ~300 ✓ run 08 gpt-mini ~300 ✓ run 09 teammate ~300 ✓ run 10 ci job ~300 ✓ first run█████████14,900 every run █ ~300
fingerprint mcp_2kLw… ✓
tool_count 79 ✓
scope readonly ✓
GATE OPEN · run v1v1 · following 8 steps
@1 ✓ @2 ✓ @3 ✓ @4 ✓
@5 ✓ @6 ✓ @7 ✓ @8 ✓
done · no reasoningRecall stops when reality changes.
- before each run, the Play checks its assumptions
- unchanged: it follows the known path, no reasoning
- changed: the agent stops following it and reasons again. the new path becomes v2
PUBLISHED PLAYS
Someone already solved it. Or you are about to.
Watch expertise evolve.
Real Plays, versioned in public. Each one ran once at full cost; every run since follows the same path for a fraction. Read the contract, run it on your own credentials, publish the next version.
Find work worth teaching.
Research-backed starting points across APIs, browsers, and local commands. Pick one, hand your agent the brief, mint the Play.
Proven once. Adopted everywhere. Your organization's expertise, kept as Plays in a private hub.
- a Play enters through the one team that already runs an agent
- it spreads to the teams that never got one, on their own harness and credentials
- the hub stays private, versioned, and yours
acme · private · 4 plays launch-readiness ●●●●● pipeline-hygiene ●●●●● incident-triage ●●●●● skills-audit ●●●●●
★≡×SALES
· · · waiting
★≡×MARKETING
· · · waiting
★≡×DEVOPS
· · · waiting
★≡×SECOPS
· · · waiting
★≡×AGENTOPS
· · · waiting
Your first Play is one run away. Install Rote, ask your agent for something real, keep what worked.
- 01INSTALLInstalls Play and Rote, detects your harness, starts guided setup.
curl -fsSL https://getrote.dev/playoffs/install.sh | sh - 02ASKAny harness. Claude Code, Codex, Cursor, Kimi, Hermes, or Pi.
$play build me a launch brief from GitHub, Linear, and Slack: what breaks if we ship Friday? - 03KEEPthe job worked. keep what made it work as a Play?▸ YES, SAVE THE PLAYPlay minted. Next runs: about 300 tokens instead of 14,900.
