Borrowing it
Nothing to install: this file belongs to marcuspat/turbo-flow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/marcuspat/turbo-flow/main/AGENTS.mdgit clone --depth 1 https://github.com/marcuspat/turbo-flowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/marcuspat/turbo-flow/agents-md)<a href="https://agentmods.dev/instructions/marcuspat/turbo-flow/agents-md"><img src="https://agentmods.dev/badge/instructions/marcuspat/turbo-flow/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/marcuspat/turbo-flow/agents-md"><img src="https://agentmods.dev/badge/instructions/marcuspat/turbo-flow/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00765 | $0.00765 |
| Opus 5.5 | $0.00306 | $0.00306 |
| Sonnet 5.5 | $0.00153 | $0.00153 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
turbo-flow AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Turbo Flow
Turbo Flow is rig-lite: a portable governance kit for AI-written code. Bash plus this file — no harness is bundled, no new dependencies. It works with whatever coding agents you already have.
This file is the source of truth for every harness.
CLAUDE.mdis a symlink to it; Codex and ZCode read it natively. Do not fork instructions per tool.
The one rule that matters
Every change is reviewed read-only by a model from a different family than the one that wrote it, and humans hold the merge button. Enforce it with the gate:
rig-lite/gate.sh --pr <n> --builder <cli> # gate a GitHub PR, verdict posted as a comment
# verdicts are pinned to the head they gated — new commits = ungated again.
# past GATE_ROUND_CAP (default 3) rounds the gate exits 4: the continue/park
# fork is the human's call (GATE_FORCE=1 overrides consciously).
rig-lite/gate.sh --base main --builder <cli> # branch mode on a working tree
The full law set lives in rig-lite/constitution.md — pair it with the gate so the laws have teeth.
Repo map
| Path | What it is |
|---|---|
rig-lite/ |
the kit: gate, worktrees, secrets, digest, token dashboard, memory pattern, spec templates, automation prompts, self-test |
demo/ |
the recorded demo + its recorder + auth-guard (refuses to record logged-in sessions) |
.devcontainer/ |
kit container: postCreate runs the self-test, installs tmux, wires the boot hook |
workspace.sh |
the 5-window tmux rig: claude · claude+ruflo · codex · tokens dashboard · shell |
Working in this repo
Use tf (one command for everything — installed by init-repo.sh to ~/.local/bin):
tf gate --builder <cli>— gate the current branch (vs main; reviewer ≠ builder's family)tf test— the fail-closed self-test suitetf secrets set/get/rm/list— encrypted secrets (names only when listing)tf wt <name>— isolated worktree per parallel writertf digest— fleet health reporttf tokens --watch— live token dashboardtf status— everything at a glance (repo, gate stats, session, tree)tf init— install the kit into any repotf protect— enable branch protection (Law 2 enforcement)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed · +3 lines · +58 tokens per session 8ee3509c1349
- 13d ago Changed · +11 lines · +117 tokens per session 76dcfbf5426b
- 20d ago Changed · +1 lines · +33 tokens per session 1405621786a5
- 22d ago First seen · 39 lines · 557 tokens per session scan A 038a537211fb
turbo-flow AGENTS.md is an instructions file published in the GitHub repository marcuspat/turbo-flow (181 stars, last pushed yesterday), licensed MIT. It adds 765 tokens to every session, about $0.0031 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-08.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.