create-roadmap

A command that turns a large software idea into a roadmap of smaller tasks arranged by dependencies. It records the roadmap in a Markdown file and prepares prompts for planning each task.

In plain words
What is it for?
Use it to break a feature, project, or other broad idea into an ordered set of tasks before running them with the related start command.
Why use it?
It removes the need to work out the task order and dependencies manually before development begins. It also separates planning the work from carrying it out.

Command 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.

agentmods
npx agentmods add commands/ayoubben18/ab-method/create-roadmap
Clone the repo
git clone --depth 1 https://github.com/ayoubben18/ab-method

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 796 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00796
Opus 5 $0.00000 $0.00398
Sonnet 5 $0.00000 $0.00159
Haiku 4.5 $0.00000 $0.00080

Measured 2d ago against content hash c9cef9dfb0ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-roadmap 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 2d 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.

.claude/commands/create-roadmap.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Roadmap

Description

Turn a larger idea into a dependency-ordered roadmap of tasks — the layer above /create-task. Grills the idea once to draw the task graph, writes roadmap.md, and hands you the per-task planning prompts. Producer only; /start-roadmap executes it.

Usage

/create-roadmap [idea]

Behavior

Loads and executes the create-roadmap workflow from .ab-method/core/create-roadmap.md.

It will:

  1. Always check .ab-method/structure/index.yaml first for paths and the relationships map.
  2. Grill the idea once (grill-with-docs, aimed at decomposition, breadth-first) — first naming the destination, then identifying discrete tasks and their depends-on edges.
  3. Write docs/roadmaps/<name>/roadmap.md — the DAG of tasks (coarse scope each, no missions), plus per-task plan: / status: fields. This is the roadmap-level source of truth. 3b. Chart only what you can see. A roadmap may be deliberately incomplete rather than complete-looking and guessed. Four optional sections, all omitted when empty (most roadmaps have none):
    • ## Open decisions — sharp questions that must be answered before the tasks they blocks: can be planned, typed grilling / research / prototype / task. One grilling-or-prototype decision per session; research runs in parallel subagents.
    • ## Decisions — the index of resolved ones, pointing at where the answer lives (an ADR, a CONTEXT.md term, a task's scope).
    • ## Not yet specified — the fog: in-scope areas you can tell are coming but can't phrase sharply yet. Graduates into tasks as answers land.
    • ## Out of scope — work ruled beyond the destination. Never graduates.
  4. Run critique-plan on the task graph — a read-only domain critic that pushes back only on genuine decomposition conflicts (wrong seams, mis-scoped tasks, boundary violations) against the domain model. Advisory; silent when the graph is sound.
  5. Emit a ready-to-paste /create-task prompt per task, in dependency order (foundational first), each seeded with the roadmap objective + upstream deps.
    • Recommended: run each in a fresh session (isolated, deep grilling).
    • Discouraged: plan inline in this session — it warns you about context bloat first.

Read the full file on GitHub · 42 lines

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. 2d ago First seen · 42 lines · 0 tokens per session scan A c9cef9dfb0ae

Subscribe to this mod's changes

create-roadmap is a command published in the GitHub repository ayoubben18/ab-method (187 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 796 tokens. 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.