⚡ TURBO FLOW — THE RULES LAYER FOR AI-WRITTEN CODE. One product lives here:
rig-lite/— a portable governance kit. It ships no harness, installs nothing, and depends only on bash. Drop it into any repo and your agents get laws with teeth.
Turbo Flow is an open-source project by Adventure Wave Labs (Marcus Patman). Versions 1–4 (2025–2026) packaged an agentic development environment around Claude Code and Ruflo — at its peak, 215+ MCP tools and 60+ agents. In September 2026 the project pivoted to a thinner, governed approach, and by v5.2 (October 2026) the orchestration stack was fully removed: Turbo Flow is now the rules layer (rig-lite), and the integrated successor, Turbo Rig, runs in private beta. Site: turboflow.online · full story: why Turbo Flow became Turbo Rig · version history.
Bring your own harness
Turbo Flow bundles no agent and no orchestrator. It names harnesses by role, and works with any tool that reads AGENTS.md and can run bash:
| Role | Who | How the kit uses it |
|---|---|---|
| Builder | ZCode (GLM), Claude Code, Codex, Gemini, Grok | gate.sh --builder <cli> knows the family; anyone can build |
| Reviewer | Claude Code or Codex CLI — never the builder's family | the gate auto-detects and refuses same-family review |
| Orchestration (optional) | Ruflo, as a Claude Code mod | bring it if you want swarms — the kit doesn't care |
ZCode builds · Claude Code reviews (Ruflo mod installed when you want orchestration) · Codex backs up the review. That loop runs in production on this repo today: every PR since rig-lite landed (v5.0) was built by one family, reviewed by another, merged by a human.
🎬 The demo — recorded in a fresh Codespace, nothing preinstalled
A clean Codespace boots this repo's devcontainer and the kit proves itself in-container — fail-closed self-test suite and a live gate run (reviewer CLI stubbed; no API keys on the recording box). Not a mockup. The recording predates the lean pivot (it shows the repo's earlier container); the current container's postCreate runs the self-test directly, and the recorder now walks that flow. Reproducible via demo/record-rig-lite-demo.sh.
🎬 The boot demo — pick a harness, get a rig
A fresh Codespace, nothing preinstalled (the recorder's three prereqs — asciinema, pexpect, agg — are documented in its header): setup-harness.sh presents the harness menu, we pick Claude Code, and node + the CLI + the Ruflo marketplace, console and mods install for real on camera — ending on the honest "claude is logged out" nudge (keys never touch the recording). One take, reproducible via demo/record-harness-boot-demo.sh.
The gate survived 17 rounds of review
rig-lite/gate.sh was itself reviewed by a model family that didn't write it — and got REVISE'd seventeen times before earning APPROVED (counted from the gate's own JSONL log). The findings are exactly the class the gate exists to catch: a prompt-injection hole that let a diff approve itself, a fail-open path that skipped review entirely, a quoting bug that swallowed failing tests, a silent-reviewer misdiagnosis. Every fix became a self-test. Builder ≠ reviewer isn't a slogan in this repo — it's the reason this script is trustworthy.
rig-lite — one kit, ten minutes, no new dependencies
| file | what it gives you |
|---|---|
gate.sh |
a cross-model review gate — deterministic checks first (they're free), then a reviewer from a different model family must return a parseable APPROVED / REVISE. Fail-closed; never merges. --pr <n> gates a GitHub PR and posts the verdict as a comment; --sweep gates every open PR that has no verdict yet; -C <repo> gates another checkout. Every verdict lands in a local JSONL log the digest joins. |
wt.sh |
an isolated worktree per parallel writer: wt <name> creates .worktrees/<name> + branch, --clean tidies up after merge. |
init-repo.sh |
one-command onboarding for any repo: a thin AGENTS.md (constitution pointer + project cheat-sheet) and the CLAUDE.md → AGENTS.md symlink. Never clobbers existing files. |
specs/ |
the spec + UAT contract templates: plan before build, verify behavior against the deployed app. |
digest.sh |
one command, one file: repo health for your whole fleet — merge queue joined with gate verdicts, merged PRs, dirty/behind working copies, site liveness, stale codespaces, repo-hygiene gaps. |
automations/ |
the background tier as a portable prompt pack: 9 scheduled tasks (morning digest, security scan, memory consolidation, weekly retro, repo-hygiene pass, site sentinel, gate canary, portability canary, nightly sweep) plus two ways to schedule them. |
secret.sh |
encrypted-at-rest secrets, backend auto-detected (macOS Keychain → libsecret → age → loudly-warned chmod-600 plaintext). set/get/rm/list — listing shows names, never values; values never appear in ps. |
memory.md + memory/ |
the git-versioned memory pattern: index, decisions, gotchas, project index, inbox — agents forget, git doesn't. |
tokens.py |
live token-burn dashboard across zcode + claude + codex + gate — reads each CLI's local usage data read-only; --watch live view, --json, TZ-pinned fixture self-test covering every adapter (including malformed-shape rows). The first open-core drop from Turbo Rig. On macOS the default run also reads the Claude OAuth token from the Keychain and calls Anthropic's usage endpoint for plan bars — --no-quota skips both. |
hooks/pre-commit |
deletion guard: staged deletions print loudly instead of silently vanishing. Warn-only, fail-open. |
constitution.md |
the laws — builder ≠ reviewer, agents never merge, worktrees for parallel writers, secrets encrypted, state on disk. |
self-test.sh |
the kit's own fail-closed test suite (hundreds of checks); says so when shellcheck-gated coverage is skipped. |
Ten-minute install
# from any repo you want to govern:
bash /path/to/turbo-flow/rig-lite/init-repo.sh # writes AGENTS.md + symlink, never clobbers
bash /path/to/turbo-flow/rig-lite/self-test.sh # prove the kit on your machine
/path/to/turbo-flow/rig-lite/gate.sh --pr 1 --builder <your-cli>
No Codespace? Fine — it's bash. Want the 30-second container tour anyway? Open this repo in a Codespace; postCreate runs the self-test. That's the whole install surface.
Your first five minutes in the rig
In a Codespace (or after running bash workspace.sh), you're inside a 5-window tmux session. Here's what to do:
1. Log in (once per box — the only manual step)
Ctrl+B 0 → jump to the claude window, type /login (browser OAuth)
Ctrl+B 4 → jump to the shell, type codex login (browser); then Ctrl+B 2
After that, every window opens ready for work, forever on this box.
2. Look around
| Keys | What you see |
|---|---|
Ctrl+B 0 |
claude — reviewer when window 1 is claude-glm; otherwise use codex (window 2) to review |
Ctrl+B 1 |
builder — claude-glm if wired, else claude with ruflo plugins loaded |
Ctrl+B 2 |
codex — your OpenAI lane (ruflo reachable via MCP) |
Ctrl+B 3 |
tokens — live burn across all three harnesses, always updating |
Ctrl+B 4 |
shell — free bash for git, builds, anything |
Ctrl+B d |
detach (come back any time — the session survives) |
3. Gate your first change
In the shell window (Ctrl+B 4), from any branch you or an agent built:
# prove the kit works:
bash rig-lite/self-test.sh
# gate a branch (the CLI that WROTE the code names itself — a different family reviews):
rig-lite/gate.sh --builder claude --base main # if claude wrote it → a non-Anthropic reviewer checks it
rig-lite/gate.sh --builder glm --base main # if claude-glm wrote it → claude reviews (cross-family)
# gate a GitHub PR (verdict posted as a comment on the PR):
rig-lite/gate.sh --pr 7 --builder codex # codex wrote it → claude reviews
# gate every open PR that has no verdict yet:
rig-lite/gate.sh --sweep
The gate exits 0 (approved) or 1 (revise — fix and re-run). It never merges; you do.
4. Your daily loop
rig-lite/wt.sh my-feature # isolated worktree for parallel work
# ... build in window 1, ask a DIFFERENT family (window 0 or 2) to read the diff ...
rig-lite/gate.sh --builder <who-wrote-it> --base main # gate before the PR
# ... push, open the PR, gate it ...
rig-lite/digest.sh # fleet health: merge queue × verdicts × site liveness
Detached and want back in? In a Codespace, every new terminal auto-attaches. Locally: run bash workspace.sh again.
Harnesses — installed by the boot, menu on demand
The kit ships no harness, and the boot no longer asks: a fresh Codespace **auto-installs the default pair (Claude Code + Codex + the Ru