A command that turns a high-level project vision into a phased roadmap, then creates larger work areas called epics and their related ideas or plans. A roadmap is an ordered view of planned work.

Use it to research a project direction, define phases and epics, generate ideas for later work, or create plans for immediate execution.

It structures an unclear vision through questioning and research before turning it into work that can enter the normal workflow or be executed immediately.

roadmap — Command by kesteva

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/kesteva/soloflow/roadmap

Clone the repo

git clone --depth 1 https://github.com/kesteva/soloflow

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,967 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.

Model	Per session	Once invoked
Fable 5	$0.00019	$0.03967
Opus 5	$0.00010	$0.01983
Sonnet 5	$0.00004	$0.00793
Haiku 4.5	$0.00002	$0.00397

Measured 2d ago against content hash 5006c4d86485, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

commands/roadmap.md · 296 lines

How it starts

The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/soloflow:roadmap

Phase 0 of the SoloFlow pipeline. Turns a high-level project vision into a phased roadmap of epics, then materializes them as ideas (for normal pipeline) or plans (for immediate execution).

The user's input is: $ARGUMENTS

Model resolution (applies to every Agent spawn below)

Before invoking the Agent tool, resolve models.<name> per the three-tier recipe in docs/CUSTOMIZATION.md#config-resolution and pass the resolved value as the Agent tool's model parameter.

Mapping used in this command:

roadmap-researcher → models.roadmap_researcher (fallback: sonnet)
roadmap-generator → models.roadmap_generator (fallback: opus)
task-refiner → models.task_refiner (fallback: opus)

Limits resolution

Resolve limits.context_limit_respawn_max (fallback: 3) at run start and use it wherever "Cap at 3 respawns" appears below.

Step 0: Initialize

If .soloflow/ does not exist, report: "SoloFlow not initialized. Run /soloflow:init first." and stop.

Step 1: Deep Questioning

Resume check: If $ARGUMENTS matches --resume ROADMAP-NNN (e.g., --resume ROADMAP-003), read .soloflow/active/roadmaps/ROADMAP-{NNN}.md. If found, skip to Step 4. If not found, report: "ROADMAP-{NNN} not found in active roadmaps." and stop.
Skip-clarify check: If $ARGUMENTS contains the literal token --skip-clarify, set clarify_enabled = false and strip the token from $ARGUMENTS. Otherwise:
- If .soloflow/config.json exists and contains phases.roadmap_clarify === false, set clarify_enabled = false.
- Else if config/defaults.yaml (via ${CLAUDE_PLUGIN_ROOT}) has phases.roadmap_clarify: false, set clarify_enabled = false.
- Otherwise clarify_enabled = true.
If clarify_enabled is false, set brief = $ARGUMENTS and proceed to Step 2.
Read ${CLAUDE_PLUGIN_ROOT}/skills/clarify-roadmap/SKILL.md via the Read tool and apply its "When to invoke" 8-point checklist against $ARGUMENTS. The checklist covers: vision, target users, constraints, success metrics, technical preferences, scope boundary, phasing priorities, risk tolerance.

Read the full file on GitHub · 296 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.

2d ago First seen · 296 lines · 19 tokens per session scan A 5006c4d86485

Subscribe to this mod's changes

roadmap is a command published in the GitHub repository kesteva/soloflow (41 stars, last pushed 3mo ago), licensed MIT. It adds 19 tokens to every session and 3,967 once invoked, about $0.0001 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.

Planning Research

roadmap

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/soloflow:roadmap

Model resolution (applies to every Agent spawn below)

Limits resolution

Step 0: Initialize

Step 1: Deep Questioning

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement