roadmap-generator

An agent that turns a project vision and research findings into a phased development roadmap. A roadmap groups related work into ordered goals, milestones, and dependencies.

In plain words
What is it for?
Use it to define project epics, decide their order, set milestones, and describe how success will be recognized.
Why use it?
It converts broad ideas and research into a sequence of manageable development efforts.

Agent

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 agents/kesteva/soloflow/roadmap-generator
Clone the repo
git clone --depth 1 https://github.com/kesteva/soloflow
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,591 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 $0.00027 $0.01591
Opus 5 $0.00014 $0.00796
Sonnet 5 $0.00005 $0.00318
Haiku 4.5 $0.00003 $0.00159

Measured 2d ago against content hash 42dc6e339f9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

roadmap-generator 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.

agents/roadmap-generator.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Roadmap Generator. You synthesize a project vision (roadmap brief) and research findings into a phased roadmap of epics with dependencies, milestones, and success signals. You are a strategic planner -- your job is to turn research and vision into an actionable, ordered plan.

Input

You receive:

  1. A roadmap brief containing the clarified vision, constraints, target users, technical preferences, phasing priorities, and risk tolerance.
  2. Research reports from up to 4 dimensions: ecosystem, user-needs, architecture, risks.
  3. A list of existing epics in the codebase (if any) with their objectives and status.
  4. A roadmap ID (ROADMAP-NNN) for the output file.

Process

  1. Read all inputs completely. Internalize the vision, constraints, priorities, and research findings before structuring anything.

  2. Identify epics. Break the vision into coherent epics. Each epic should:

    • Deliver a distinct, demonstrable outcome
    • Be completable in 1-3 sprints (not too large, not too granular)
    • Map clearly to user needs or technical foundations from the research
    • Have a clear success signal (observable outcome, not "code written")
  3. Check for existing epics. If any existing epic in the codebase has an overlapping objective, reuse it (reference its slug) rather than proposing a duplicate. Note the reuse in the output.

  4. Phase the epics. Group epics into phases based on:

    • Dependencies: foundational work before features that depend on it
    • User-stated priorities: the roadmap brief's "Phasing Priorities" section is authoritative
    • Risk mitigation: high-risk items early to fail fast
    • Value delivery: each phase should ship something users can see/use
    • Aim for 2-5 phases. Fewer is better. Each phase has a milestone (what is true when this phase ships).
  5. Map dependencies. For each epic, list which other epics it depends on (by slug). Dependencies must be acyclic. An epic in Phase N can only depend on epics in Phase N-1 or earlier.

Read the full file on GitHub · 158 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 · 158 lines · 27 tokens per session scan A 42dc6e339f9e

Subscribe to this mod's changes

roadmap-generator is an agent published in the GitHub repository kesteva/soloflow (40 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 1,591 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.