aidoc-flow

A preview workflow for specification-driven development: planning and building software from a chain of documents, from a business requirements document to an implementation plan. It includes skills, agents, and commands for that document flow.

In plain words
What is it for?
Use it to create or manage business requirements, product requirements, behavior specifications, architecture decisions, tests, and implementation plans through the eight-layer document process.
Why use it?
It helps teams turn broad ideas into progressively more detailed specifications before implementation, while keeping the workflow organized.

Plugin for Claude Code

Install

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.

Claude Code
/plugin marketplace add vladm3105/aidoc-flow-framework
agentmods
npx agentmods add plugins/vladm3105/aidoc-flow-framework/claude-code-plugin
Clone the repo
git clone --depth 1 https://github.com/vladm3105/aidoc-flow-framework

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

aidoc-flow 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 yesterday.

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.

platforms/claude-code-plugin/.claude-plugin/plugin.json · 15 lines

What it actually says

{
  "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
  "name": "aidoc-flow",
  "description": "Pre-1.0 preview. AI-Driven Specification-Driven Development (SDD) workflow — skills, agents, and commands for the 8-layer doc flow (BRD → IPLAN). Consumes the aidoc-flow framework spec. The doc-*-autopilot skills opt in to running their dispatched subprocesses without permission prompts; see README \"What the autopilot skills do to your permissions\". APIs and surfaces may change before 1.0.",
  "version": "0.25.0",
  "author": {
    "name": "AI Doc Flow",
    "url": "https://github.com/vladm3105/aidoc-flow-framework"
  },
  "license": "MIT",
  "repository": "https://github.com/vladm3105/aidoc-flow-framework",
  "homepage": "https://github.com/vladm3105/aidoc-flow-framework#install-the-claude-code-plugin",
  "keywords": ["sdd", "spec-driven-development", "documentation", "brd", "prd", "ears", "bdd", "adr", "spec", "tdd", "iplan"]
}
Changes

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.

  1. yesterday First seen · 15 lines scan A 14469bc2c50b

Subscribe to this mod's changes

aidoc-flow is a plugin published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.