Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/ljtian/maker-flow/agents-mdgit clone --depth 1 https://github.com/LJTian/maker-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/ljtian/maker-flow/agents-md)<a href="https://agentmods.dev/instructions/ljtian/maker-flow/agents-md"><img src="https://agentmods.dev/badge/instructions/ljtian/maker-flow/agents-md.svg" alt="Measured on agentmods" 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 | $0.01215 | $0.01215 |
| Opus 5 | $0.00607 | $0.00607 |
| Sonnet 5 | $0.00243 | $0.00243 |
| Haiku 4.5 | $0.00121 | $0.00121 |
Grade A, and why
maker-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 4d ago.
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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — factory (maker-flow tool repo)
English · 简体中文
Audience: AI agents working on this factory repo only.
For MVP product work, open a product repo (maker-flow new <name>) and use its AGENTS.md (from AGENTS.consumer.example.md).
Human intro: README.md · Quick start: docs/getting-started.md · Product repos: docs/consumer-project.md · i18n: docs/i18n.md
This repository is an agent playbook for shipping personal MVPs. Humans only provide requirements and approve gates.
Layout: parallel product repos — read consumer-project.md; use AGENTS.consumer.example.md in each MVP repo (maker-flow new <name>). Assembled MVPs MUST NOT be written into this factory repo.
Principle: heavy infrastructure, light logic. Prefer templates and skills over inventing scaffolding.
Language
- Canonical contracts are the English
.mdfiles. .zh-CN.mdsiblings are for humans only.- MUST NOT treat Chinese siblings as authoritative for steps, skills, or gates unless the human explicitly asks for Chinese-facing output.
Agent entry
- Read
docs/workflow.md(state machine + hard gates). - Load the skill for the current step from
skills/(start atskills/CATALOG.md). - Use inputs from
prompts/(or user message equivalent). - For step 4, open
templates/CATALOG.mdbefore matching. - Write outputs to the paths defined by the skill.
Do not skip gates. Do not invent a new stack when templates/index.md has a match.
Six-step state machine
| Step | Actor | Action | Required reads | Output |
|---|---|---|---|---|
| 1 | Human | Provide requirement | — | requirement text |
| 2 | Agent | Draft PRO | skills/pro-generation.md, prompts/02-pro-draft.md, prompts/pro.template.md |
PRO markdown (no code) |
| 3 | Human | Approve PRO | — | confirmed PRO → prompts/03-pro-confirmed.example.md or project pro.md (same shape as pro.template.md) |
| 4 | Agent | Match template + assemble MVP | skills/template-matching.md, skills/mvp-assembly.md, templates/index.md, prompts/04-assemble-mvp.md |
Product repo root (maker-flow new <name>) |
| 5 | Human | Approve MVP | skills/mvp-acceptance.md, prompts/05-accept-mvp.md, product pro.md |
pass/fail (+ agent evidence package) |
| 6 | Agent (on approve) | Publish | skills/deploy.md, prompts/06-publish.md, skills/publish-<target>.md |
public URL(s) |
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.
- 4d ago First seen · 82 lines · 1,215 tokens per session scan A 4ec16fa842c7
maker-flow AGENTS.md is an instructions file published in the GitHub repository LJTian/maker-flow (151 stars, last pushed 21d ago), licensed MIT. It adds 1,215 tokens to every session, about $0.0061 per session on Opus 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 2026-08-30.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.